Publish version 0.1.8.

We are properly handling this currently, but it is good to have more test coverage.

.lighthouse/pipeline-foreign-document-test.yaml

@@ -0,0 +1,203 @@
+apiVersion: tekton.dev/v1beta1
+kind: PipelineRun
+metadata:
+  name: rust-foreign-document-test
+spec:
+  pipelineSpec:
+    timeouts:
+      pipeline: "2h0m0s"
+      tasks: "1h0m40s"
+      finally: "0h30m0s"
+    params:
+      - name: image-name
+        description: The name for the built image
+        type: string
+      - name: path-to-image-context
+        description: The path to the build context
+        type: string
+      - name: path-to-dockerfile
+        description: The path to the Dockerfile
+        type: string
+    tasks:
+      - name: do-stuff
+        taskSpec:
+          metadata: {}
+          stepTemplate:
+            image: alpine:3.18
+            name: ""
+            resources:
+              requests:
+                cpu: 10m
+                memory: 600Mi
+            workingDir: /workspace/source
+          steps:
+            - image: alpine:3.18
+              name: do-stuff-step
+              script: |
+                #!/usr/bin/env sh
+                echo "hello world"
+      - name: report-pending
+        taskRef:
+          name: gitea-set-status
+        runAfter:
+          - fetch-repository
+        params:
+          - name: CONTEXT
+            value: "$(params.JOB_NAME)"
+          - name: REPO_FULL_NAME
+            value: "$(params.REPO_OWNER)/$(params.REPO_NAME)"
+          - name: GITEA_HOST_URL
+            value: code.fizz.buzz
+          - name: SHA
+            value: "$(tasks.fetch-repository.results.commit)"
+          - name: DESCRIPTION
+            value: "Build $(params.JOB_NAME) has started"
+          - name: STATE
+            value: pending
+          - name: TARGET_URL
+            value: "https://tekton.fizz.buzz/#/namespaces/$(context.pipelineRun.namespace)/pipelineruns/$(context.pipelineRun.name)"
+      - name: fetch-repository
+        taskRef:
+          name: git-clone
+        workspaces:
+          - name: output
+            workspace: git-source
+        params:
+          - name: url
+            value: $(params.REPO_URL)
+          - name: revision
+            value: $(params.PULL_BASE_SHA)
+          - name: deleteExisting
+            value: "true"
+      - name: build-image
+        taskRef:
+          name: kaniko
+        params:
+          - name: IMAGE
+            value: "$(params.image-name):$(tasks.fetch-repository.results.commit)"
+          - name: CONTEXT
+            value: $(params.path-to-image-context)
+          - name: DOCKERFILE
+            value: $(params.path-to-dockerfile)
+          - name: BUILDER_IMAGE
+            value: "gcr.io/kaniko-project/executor:v1.12.1"
+          - name: EXTRA_ARGS
+            value:
+              - --target=foreign-document-test
+              - --cache=true
+              - --cache-copy-layers
+              - --cache-repo=harbor.fizz.buzz/kanikocache/cache
+              - --use-new-run # Should result in a speed-up
+              - --reproducible # To remove timestamps so layer caching works.
+              - --snapshot-mode=redo
+              - --skip-unused-stages=true
+              - --registry-mirror=dockerhub.dockerhub.svc.cluster.local
+        workspaces:
+          - name: source
+            workspace: git-source
+          - name: dockerconfig
+            workspace: docker-credentials
+        runAfter:
+          - fetch-repository
+      - name: run-image
+        taskRef:
+          name: run-docker-image
+        workspaces:
+          - name: source
+            workspace: git-source
+          - name: cargo-cache
+            workspace: cargo-cache
+        runAfter:
+          - build-image
+        params:
+          - name: docker-image
+            value: "$(params.image-name):$(tasks.fetch-repository.results.commit)"
+    finally:
+      - name: report-success
+        when:
+          - input: "$(tasks.status)"
+            operator: in
+            values: ["Succeeded", "Completed"]
+        taskRef:
+          name: gitea-set-status
+        params:
+          - name: CONTEXT
+            value: "$(params.JOB_NAME)"
+          - name: REPO_FULL_NAME
+            value: "$(params.REPO_OWNER)/$(params.REPO_NAME)"
+          - name: GITEA_HOST_URL
+            value: code.fizz.buzz
+          - name: SHA
+            value: "$(tasks.fetch-repository.results.commit)"
+          - name: DESCRIPTION
+            value: "Build $(params.JOB_NAME) has succeeded"
+          - name: STATE
+            value: success
+          - name: TARGET_URL
+            value: "https://tekton.fizz.buzz/#/namespaces/$(context.pipelineRun.namespace)/pipelineruns/$(context.pipelineRun.name)"
+      - name: report-failure
+        when:
+          - input: "$(tasks.status)"
+            operator: in
+            values: ["Failed"]
+        taskRef:
+          name: gitea-set-status
+        params:
+          - name: CONTEXT
+            value: "$(params.JOB_NAME)"
+          - name: REPO_FULL_NAME
+            value: "$(params.REPO_OWNER)/$(params.REPO_NAME)"
+          - name: GITEA_HOST_URL
+            value: code.fizz.buzz
+          - name: SHA
+            value: "$(tasks.fetch-repository.results.commit)"
+          - name: DESCRIPTION
+            value: "Build $(params.JOB_NAME) has failed"
+          - name: STATE
+            value: failure
+          - name: TARGET_URL
+            value: "https://tekton.fizz.buzz/#/namespaces/$(context.pipelineRun.namespace)/pipelineruns/$(context.pipelineRun.name)"
+      - name: cargo-cache-autoclean
+        taskRef:
+          name: run-docker-image
+        workspaces:
+          - name: source
+            workspace: git-source
+          - name: cargo-cache
+            workspace: cargo-cache
+        params:
+          - name: command
+            value: [cargo, cache, --autoclean]
+          - name: args
+            value: []
+          - name: docker-image
+            value: "$(params.image-name):$(tasks.fetch-repository.results.commit)"
+    workspaces:
+      - name: git-source
+      - name: docker-credentials
+      - name: cargo-cache
+  workspaces:
+    - name: git-source
+      volumeClaimTemplate:
+        spec:
+          storageClassName: "nfs-client"
+          accessModes:
+            - ReadWriteOnce
+          resources:
+            requests:
+              storage: 10Gi
+      subPath: rust-source
+    - name: cargo-cache
+      persistentVolumeClaim:
+        claimName: organic-cargo-cache-test-foreign-document
+    - name: docker-credentials
+      secret:
+        secretName: harbor-plain
+  serviceAccountName: build-bot
+  params:
+    - name: image-name
+      value: "harbor.fizz.buzz/private/organic-test-foreign-document"
+    - name: path-to-image-context
+      value: docker/organic_test/
+    - name: path-to-dockerfile
+      value: docker/organic_test/Dockerfile

.lighthouse/pipeline-rust-test.yaml

@@ -83,6 +83,7 @@ spec:
             value: "gcr.io/kaniko-project/executor:v1.12.1"
           - name: EXTRA_ARGS
             value:
+              - --target=tester
               - --cache=true
               - --cache-copy-layers
               - --cache-repo=harbor.fizz.buzz/kanikocache/cache

.lighthouse/triggers.yaml

@@ -16,6 +16,13 @@ spec:
       skip_branches:
         # We already run on every commit, so running when the semver tags get pushed is causing needless double-processing.
         - "^v[0-9]+\\.[0-9]+\\.[0-9]+$"
+    - name: rust-foreign-document-test
+      source: "pipeline-foreign-document-test.yaml"
+      # Override https-based url from lighthouse events.
+      clone_uri: "git@code.fizz.buzz:talexander/organic.git"
+      skip_branches:
+        # We already run on every commit, so running when the semver tags get pushed is causing needless double-processing.
+        - "^v[0-9]+\\.[0-9]+\\.[0-9]+$"
     - name: rust-build
       source: "pipeline-rust-build.yaml"
       # Override https-based url from lighthouse events.

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "organic"
-version = "0.1.4"
+version = "0.1.8"
 authors = ["Tom Alexander <tom@fizz.buzz>"]
 description = "An org-mode parser."
 edition = "2021"
@@ -21,9 +21,15 @@ name = "organic"
 path = "src/lib.rs"
 
 [[bin]]
-# This bin exists for development purposes only. The real target of this crate is the library.
-name = "compare"
-path = "src/main.rs"
+  # This bin exists for development purposes only. The real target of this crate is the library.
+  name = "parse"
+  path = "src/main.rs"
+
+[[bin]]
+  # This bin exists for development purposes only. The real target of this crate is the library.
+  name = "compare"
+  path = "src/bin_compare.rs"
+  required-features = ["compare"]
 
 [dependencies]
 nom = "7.1.1"

Makefile

@@ -33,6 +33,10 @@ release:
 clean:
 > cargo clean
 
+.PHONY: format
+format:
+> $(MAKE) -C docker/cargo_fmt run
+
 .PHONY: test
 test:
 > cargo test --no-default-features --features compare --no-fail-fast --lib --test test_loader -- --test-threads $(TESTJOBS)
@@ -40,7 +44,11 @@ test:
 .PHONY: dockertest
 dockertest:
 > $(MAKE) -C docker/organic_test
-> docker run --init --rm -i -t -v "$$(readlink -f ./):/source:ro" --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target -w /source organic-test --no-default-features --features compare --no-fail-fast --lib --test test_loader -- --test-threads $(TESTJOBS)
+> docker run --init --rm -i -t --read-only -v "$$(readlink -f ./):/source:ro" --mount type=tmpfs,destination=/tmp --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target -w /source organic-test --no-default-features --features compare --no-fail-fast --lib --test test_loader -- --test-threads $(TESTJOBS)
+
+.PHONY: foreign_document_test
+foreign_document_test:
+> $(MAKE) -C docker/organic_test run_foreign_document_test
 
 .PHONY: dockerclean
 dockerclean:
@@ -60,7 +68,7 @@ jaeger:
 # 4317 for OTLP gRPC, 4318 for OTLP HTTP. We currently use gRPC but I forward both ports regardless.
 #
 # These flags didn't help even though they seem like they would: --collector.queue-size=20000 --collector.num-workers=100
-> docker run -d --rm --name organicdocker -p 4317:4317 -p 4318:4318 -p 16686:16686 -e COLLECTOR_OTLP_ENABLED=true jaegertracing/all-in-one:1.47 --collector.grpc-server.max-message-size=20000000 --collector.otlp.grpc.max-message-size=20000000
+> docker run -d --rm --name organicdocker --read-only -p 4317:4317 -p 4318:4318 -p 16686:16686 -e COLLECTOR_OTLP_ENABLED=true jaegertracing/all-in-one:1.47 --collector.grpc-server.max-message-size=20000000 --collector.otlp.grpc.max-message-size=20000000
 
 .PHONY: jaegerweb
 jaegerweb:

README.md

@@ -2,12 +2,63 @@
 
 Organic is an emacs-less implementation of an [org-mode](https://orgmode.org/) parser.
 
-
 ## Project Status
 
 This project is a personal learning project to grow my experience in [rust](https://www.rust-lang.org/). It is under development and at this time I would not recommend anyone use this code. The goal is to turn this into a project others can use, at which point more information will appear in this README.
 
+## Using this library
+TODO: Add section on using Organic as a library (which is the intended use for this project).
+
+### The parse binary
+This program takes org-mode input either streamed in on stdin or as paths to files passed in as arguments. It then parses them using Organic and dumps the result to stdout. This program is intended solely as a development tool. Examples:
+```bash
+cat /foo/bar.org | cargo run --bin parse
+```
+```bash
+cargo build --profile release-lto
+./target/release-lto/parse /foo/bar.org /lorem/ipsum.org
+```
+
+### The compare binary
+This program takes org-mode input either streamed in on stdin or as paths to files passed in as arguments. It then parses them using Organic and the official Emacs Org-mode parser and compares the parse result. This program is intended solely as a development tool. Since org-mode is a moving target, it is recommended that you run this through docker since we pin the version of org-mode to a specific revision. Examples:
+```bash
+cat /foo/bar.org | ./scripts/run_docker_compare.bash
+```
+```bash
+./scripts/run_docker_compare.bash /foo/bar.org /lorem/ipsum.org
+```
+
+Not recommended since it is not through docker:
+
+```bash
+cat /foo/bar.org | cargo run --features compare --bin compare
+```
+```bash
+cargo build --profile release-lto --features compare
+./target/release-lto/compare /foo/bar.org /lorem/ipsum.org
+```
+
+## Running the tests
+There are three levels of tests for this repository: the standard tests, the autogenerated tests, and the foreign document tests.
+
+### The standard tests
+These are regular hand-written rust tests. These can be run with:
+```bash
+make unittest
+```
+
+### The auto-generated tests
+These tests are automatically generated from the files in the `org_mode_samples` directory and they are still integrated with the rust/cargo testing framework. For each org-mode document in that folder, a test is generated that will parse the document with both Organic and the official Emacs Org-mode parser and then it will compare the parse results. Any deviation is considered a failure. Since org-mode is a moving target, it is recommended that you run these tests inside docker since the `organic-test` docker image is pinned to a specific revision of org-mode. These can be run with:
+```bash
+make dockertest
+```
+
+### The foreign document tests
+These tests function the same as the auto-generated tests except they are **not** integrated with the rust/cargo testing framework and they involve comparing the parse of org-mode documents that live outside this repository. This allows us to test against a far greater variety of org-mode input documents without pulling massive sets of org-mode documents into this repository. The recommended way to run these tests is still through docker because it pins org-mode and the test documents to specific git revisions. These can be run with:
+```bash
+make foreign_document_test
+```
 
 ## License
 
-This project is released under the public-domain-equivalent [0BSD license](https://www.tldrlegal.com/license/bsd-0-clause-license). This license puts no restrictions on the use of this code (you do not even have to include the copyright notice or license text when using it). HOWEVER, this project has a couple permissively licensed dependencies which do require their copyright notices and/or license texts to be included. I am not a lawyer and this is not legal advice but it is my layperson's understanding that if you distribute a binary with this library linked in, you will need to abide by their terms since their code will also be linked in your binary. I try to keep the dependencies to a minimum and the most restrictive dependency I will ever include is a permissively licensed one.
+This project is released under the public-domain-equivalent [0BSD license](https://www.tldrlegal.com/license/bsd-0-clause-license), however, this project has a couple permissively licensed non-public-domain-equivalent dependencies which require their copyright notices and/or license texts to be included. I am not a lawyer and this is not legal advice but it is my layperson's understanding that if you distribute a binary statically linking this library, you will need to abide by their terms since their code will also be linked in your binary.

build.rs

@@ -16,6 +16,9 @@ fn main() {
     let destination = Path::new(&out_dir).join("tests.rs");
     let mut test_file = File::create(&destination).unwrap();
 
+    // Re-generate the tests if any org-mode files change
+    println!("cargo:rerun-if-changed=org_mode_samples");
+
     write_header(&mut test_file);
 
     let test_files = WalkDir::new("org_mode_samples")
@@ -71,10 +74,6 @@ fn write_header(test_file: &mut File) {
         test_file,
         r#"
 #[feature(exit_status_error)]
-use organic::compare_document;
-use organic::parser::document;
-use organic::emacs_parse_org_document;
-use organic::parser::sexp::sexp_with_padding;
 
 "#
     )
@@ -86,8 +85,6 @@ fn is_expect_fail(name: &str) -> Option<&str> {
     match name {
         "autogen_greater_element_drawer_drawer_with_headline_inside" => Some("Apparently lines with :end: become their own paragraph. This odd behavior needs to be investigated more."),
         "autogen_element_container_priority_footnote_definition_dynamic_block" => Some("Apparently broken begin lines become their own paragraph."),
-        "autogen_lesser_element_paragraphs_paragraph_with_backslash_line_breaks" => Some("The text we're getting out of the parse tree is already processed to remove line breaks, so our comparison needs to take that into account."),
-        "autogen_unicode_hearts" => Some("Unicode is coming out of emacs strange."),
         _ => None,
     }
 }

docker/cargo_fmt/Makefile

@@ -6,7 +6,7 @@ all: build push
 
 .PHONY: build
 build:
-	docker build -t $(IMAGE_NAME) -f Dockerfile ../../
+	docker build -t $(IMAGE_NAME) -f Dockerfile .
 
 .PHONY: push
 push:
@@ -29,8 +29,8 @@ endif
 # NOTE: This target will write to folders underneath the git-root
 .PHONY: run
 run: build
-	docker run --rm --init -v "$$(readlink -f ../../):/source" --workdir=/source $(IMAGE_NAME)
+	docker run --rm --init --read-only --mount type=tmpfs,destination=/tmp -v "$$(readlink -f ../../):/source" --workdir=/source $(IMAGE_NAME)
 
 .PHONY: shell
 shell: build
-	docker run --rm -i -t --entrypoint /bin/sh -v "$$(readlink -f ../../):/source" --workdir=/source $(IMAGE_NAME)
+	docker run --rm -i -t --entrypoint /bin/sh --mount type=tmpfs,destination=/tmp -v "$$(readlink -f ../../):/source" --workdir=/source $(IMAGE_NAME)

docker/organic_build/Makefile

@@ -6,7 +6,7 @@ all: build push
 
 .PHONY: build
 build:
-	docker build -t $(IMAGE_NAME) -f Dockerfile ../../
+	docker build -t $(IMAGE_NAME) -f Dockerfile .
 
 .PHONY: push
 push:
@@ -30,8 +30,8 @@ endif
 # NOTE: This target will write to folders underneath the git-root
 .PHONY: run
 run: build
-	docker run --rm --init -v "$$(readlink -f ../../):/source" --workdir=/source --mount source=cargo-cache,target=/usr/local/cargo/registry $(IMAGE_NAME)
+	docker run --rm --init --read-only --mount type=tmpfs,destination=/tmp -v "$$(readlink -f ../../):/source" --workdir=/source --mount source=cargo-cache,target=/usr/local/cargo/registry $(IMAGE_NAME)
 
 .PHONY: shell
 shell: build
-	docker run --rm -i -t --entrypoint /bin/sh -v "$$(readlink -f ../../):/source" --workdir=/source --mount source=cargo-cache,target=/usr/local/cargo/registry $(IMAGE_NAME)
+	docker run --rm -i -t --entrypoint /bin/sh --mount type=tmpfs,destination=/tmp -v "$$(readlink -f ../../):/source" --workdir=/source --mount source=cargo-cache,target=/usr/local/cargo/registry $(IMAGE_NAME)

docker/organic_test/Dockerfile

@@ -1,5 +1,5 @@
 FROM alpine:3.17 AS build
-RUN apk add --no-cache build-base musl-dev git autoconf make texinfo gnutls-dev ncurses-dev gawk
+RUN apk add --no-cache build-base musl-dev git autoconf make texinfo gnutls-dev ncurses-dev gawk libgccjit-dev
 
 
 FROM build AS build-emacs
@@ -8,13 +8,13 @@ RUN git clone --depth 1 --branch $EMACS_VERSION https://git.savannah.gnu.org/git
 WORKDIR /root/emacs
 RUN mkdir /root/dist
 RUN ./autogen.sh
-RUN ./configure --prefix /usr --without-x --without-sound
+RUN ./configure --prefix /usr --without-x --without-sound --with-native-compilation=aot
 RUN make
 RUN make DESTDIR="/root/dist" install
 
 
 FROM build AS build-org-mode
-ARG ORG_VERSION=7bdec435ff5d86220d13c431e799c5ed44a57da1
+ARG ORG_VERSION=c703541ffcc14965e3567f928de1683a1c1e33f6
 COPY --from=build-emacs /root/dist/ /
 RUN mkdir /root/dist
 # Savannah does not allow fetching specific revisions, so we're going to have to put unnecessary load on their server by cloning main and then checking out the revision we want.
@@ -25,10 +25,83 @@ RUN make compile
 RUN make DESTDIR="/root/dist" install
 
 
-FROM rustlang/rust:nightly-alpine3.17
-RUN apk add --no-cache musl-dev ncurses gnutls
+FROM rustlang/rust:nightly-alpine3.17 AS tester
+ENV LANG=en_US.UTF-8
+RUN apk add --no-cache musl-dev ncurses gnutls libgccjit
 RUN cargo install --locked --no-default-features --features ci-autoclean cargo-cache
 COPY --from=build-emacs /root/dist/ /
 COPY --from=build-org-mode /root/dist/ /
 
 ENTRYPOINT ["cargo", "test"]
+
+
+FROM build as foreign-document-gather
+
+ARG HOWARD_ABRAMS_DOT_FILES_VERSION=1b54fe75d74670dc7bcbb6b01ea560c45528c628
+ARG HOWARD_ABRAMS_DOT_FILES_PATH=/foreign_documents/howardabrams/dot-files
+ARG HOWARD_ABRAMS_DOT_FILES_REPO=https://github.com/howardabrams/dot-files.git
+RUN mkdir /foreign_documents
+RUN mkdir -p $HOWARD_ABRAMS_DOT_FILES_PATH && git -C $HOWARD_ABRAMS_DOT_FILES_PATH init --initial-branch=main && git -C $HOWARD_ABRAMS_DOT_FILES_PATH remote add origin $HOWARD_ABRAMS_DOT_FILES_REPO && git -C $HOWARD_ABRAMS_DOT_FILES_PATH fetch origin $HOWARD_ABRAMS_DOT_FILES_VERSION && git -C $HOWARD_ABRAMS_DOT_FILES_PATH checkout FETCH_HEAD
+
+ARG HOWARD_ABRAMS_HAMACS_VERSION=da51188cc195d41882175d412fe40a8bc5730c5c
+ARG HOWARD_ABRAMS_HAMACS_PATH=/foreign_documents/howardabrams/hamacs
+ARG HOWARD_ABRAMS_HAMACS_REPO=https://github.com/howardabrams/hamacs.git
+RUN mkdir -p $HOWARD_ABRAMS_HAMACS_PATH && git -C $HOWARD_ABRAMS_HAMACS_PATH init --initial-branch=main && git -C $HOWARD_ABRAMS_HAMACS_PATH remote add origin $HOWARD_ABRAMS_HAMACS_REPO && git -C $HOWARD_ABRAMS_HAMACS_PATH fetch origin $HOWARD_ABRAMS_HAMACS_VERSION && git -C $HOWARD_ABRAMS_HAMACS_PATH checkout FETCH_HEAD
+
+ARG HOWARD_ABRAMS_DEMO_IT_VERSION=e399fd7ceb73caeae7cb50b247359bafcaee2a3f
+ARG HOWARD_ABRAMS_DEMO_IT_PATH=/foreign_documents/howardabrams/demo-it
+ARG HOWARD_ABRAMS_DEMO_IT_REPO=https://github.com/howardabrams/demo-it.git
+RUN mkdir -p $HOWARD_ABRAMS_DEMO_IT_PATH && git -C $HOWARD_ABRAMS_DEMO_IT_PATH init --initial-branch=main && git -C $HOWARD_ABRAMS_DEMO_IT_PATH remote add origin $HOWARD_ABRAMS_DEMO_IT_REPO && git -C $HOWARD_ABRAMS_DEMO_IT_PATH fetch origin $HOWARD_ABRAMS_DEMO_IT_VERSION && git -C $HOWARD_ABRAMS_DEMO_IT_PATH checkout FETCH_HEAD
+
+ARG HOWARD_ABRAMS_MAGIT_DEMO_VERSION=59e82f6bc7c18f550478d86a8f680c3f2da66985
+ARG HOWARD_ABRAMS_MAGIT_DEMO_PATH=/foreign_documents/howardabrams/magit-demo
+ARG HOWARD_ABRAMS_MAGIT_DEMO_REPO=https://github.com/howardabrams/magit-demo.git
+RUN mkdir -p $HOWARD_ABRAMS_MAGIT_DEMO_PATH && git -C $HOWARD_ABRAMS_MAGIT_DEMO_PATH init --initial-branch=main && git -C $HOWARD_ABRAMS_MAGIT_DEMO_PATH remote add origin $HOWARD_ABRAMS_MAGIT_DEMO_REPO && git -C $HOWARD_ABRAMS_MAGIT_DEMO_PATH fetch origin $HOWARD_ABRAMS_MAGIT_DEMO_VERSION && git -C $HOWARD_ABRAMS_MAGIT_DEMO_PATH checkout FETCH_HEAD
+
+ARG HOWARD_ABRAMS_PDX_EMACS_HACKERS_VERSION=bfb7bd640fdf0ce3def21f9fc591ed35d776b26d
+ARG HOWARD_ABRAMS_PDX_EMACS_HACKERS_PATH=/foreign_documents/howardabrams/pdx-emacs-hackers
+ARG HOWARD_ABRAMS_PDX_EMACS_HACKERS_REPO=https://github.com/howardabrams/pdx-emacs-hackers.git
+RUN mkdir -p $HOWARD_ABRAMS_PDX_EMACS_HACKERS_PATH && git -C $HOWARD_ABRAMS_PDX_EMACS_HACKERS_PATH init --initial-branch=main && git -C $HOWARD_ABRAMS_PDX_EMACS_HACKERS_PATH remote add origin $HOWARD_ABRAMS_PDX_EMACS_HACKERS_REPO && git -C $HOWARD_ABRAMS_PDX_EMACS_HACKERS_PATH fetch origin $HOWARD_ABRAMS_PDX_EMACS_HACKERS_VERSION && git -C $HOWARD_ABRAMS_PDX_EMACS_HACKERS_PATH checkout FETCH_HEAD
+
+ARG HOWARD_ABRAMS_FLORA_SIMULATOR_VERSION=50de13068722b9e3878f8598b749b7ccd14e7f8e
+ARG HOWARD_ABRAMS_FLORA_SIMULATOR_PATH=/foreign_documents/howardabrams/flora-simulator
+ARG HOWARD_ABRAMS_FLORA_SIMULATOR_REPO=https://github.com/howardabrams/flora-simulator.git
+RUN mkdir -p $HOWARD_ABRAMS_FLORA_SIMULATOR_PATH && git -C $HOWARD_ABRAMS_FLORA_SIMULATOR_PATH init --initial-branch=main && git -C $HOWARD_ABRAMS_FLORA_SIMULATOR_PATH remote add origin $HOWARD_ABRAMS_FLORA_SIMULATOR_REPO && git -C $HOWARD_ABRAMS_FLORA_SIMULATOR_PATH fetch origin $HOWARD_ABRAMS_FLORA_SIMULATOR_VERSION && git -C $HOWARD_ABRAMS_FLORA_SIMULATOR_PATH checkout FETCH_HEAD
+
+ARG HOWARD_ABRAMS_LITERATE_DEVOPS_DEMO_VERSION=2d7a5e41001a1adf7ec24aeb6acc8525a72d7892
+ARG HOWARD_ABRAMS_LITERATE_DEVOPS_DEMO_PATH=/foreign_documents/howardabrams/literate-devops-demo
+ARG HOWARD_ABRAMS_LITERATE_DEVOPS_DEMO_REPO=https://github.com/howardabrams/literate-devops-demo.git
+RUN mkdir -p $HOWARD_ABRAMS_LITERATE_DEVOPS_DEMO_PATH && git -C $HOWARD_ABRAMS_LITERATE_DEVOPS_DEMO_PATH init --initial-branch=main && git -C $HOWARD_ABRAMS_LITERATE_DEVOPS_DEMO_PATH remote add origin $HOWARD_ABRAMS_LITERATE_DEVOPS_DEMO_REPO && git -C $HOWARD_ABRAMS_LITERATE_DEVOPS_DEMO_PATH fetch origin $HOWARD_ABRAMS_LITERATE_DEVOPS_DEMO_VERSION && git -C $HOWARD_ABRAMS_LITERATE_DEVOPS_DEMO_PATH checkout FETCH_HEAD
+
+ARG HOWARD_ABRAMS_CLOJURE_YESQL_XP_VERSION=b651c7f8b47b2710e99fce9652980902bbc1c6c9
+ARG HOWARD_ABRAMS_CLOJURE_YESQL_XP_PATH=/foreign_documents/howardabrams/clojure-yesql-xp
+ARG HOWARD_ABRAMS_CLOJURE_YESQL_XP_REPO=https://github.com/howardabrams/clojure-yesql-xp.git
+RUN mkdir -p $HOWARD_ABRAMS_CLOJURE_YESQL_XP_PATH && git -C $HOWARD_ABRAMS_CLOJURE_YESQL_XP_PATH init --initial-branch=main && git -C $HOWARD_ABRAMS_CLOJURE_YESQL_XP_PATH remote add origin $HOWARD_ABRAMS_CLOJURE_YESQL_XP_REPO && git -C $HOWARD_ABRAMS_CLOJURE_YESQL_XP_PATH fetch origin $HOWARD_ABRAMS_CLOJURE_YESQL_XP_VERSION && git -C $HOWARD_ABRAMS_CLOJURE_YESQL_XP_PATH checkout FETCH_HEAD
+
+ARG HOWARD_ABRAMS_VEEP_VERSION=e37fcf63a5c4a526255735ee34955528b3b280ae
+ARG HOWARD_ABRAMS_VEEP_PATH=/foreign_documents/howardabrams/veep
+ARG HOWARD_ABRAMS_VEEP_REPO=https://github.com/howardabrams/veep.git
+RUN mkdir -p $HOWARD_ABRAMS_VEEP_PATH && git -C $HOWARD_ABRAMS_VEEP_PATH init --initial-branch=main && git -C $HOWARD_ABRAMS_VEEP_PATH remote add origin $HOWARD_ABRAMS_VEEP_REPO && git -C $HOWARD_ABRAMS_VEEP_PATH fetch origin $HOWARD_ABRAMS_VEEP_VERSION && git -C $HOWARD_ABRAMS_VEEP_PATH checkout FETCH_HEAD
+
+ARG DOOMEMACS_VERSION=42d5fd83504f8aa80f3248036006fbcd49222943
+ARG DOOMEMACS_PATH=/foreign_documents/doomemacs
+ARG DOOMEMACS_REPO=https://github.com/doomemacs/doomemacs.git
+RUN mkdir -p $DOOMEMACS_PATH && git -C $DOOMEMACS_PATH init --initial-branch=main && git -C $DOOMEMACS_PATH remote add origin $DOOMEMACS_REPO && git -C $DOOMEMACS_PATH fetch origin $DOOMEMACS_VERSION && git -C $DOOMEMACS_PATH checkout FETCH_HEAD
+
+ARG WORG_VERSION=0c8d5679b536af450b61812246a3e02b8103f4b8
+ARG WORG_PATH=/foreign_documents/worg
+ARG WORG_REPO=https://git.sr.ht/~bzg/worg
+RUN mkdir -p $WORG_PATH && git -C $WORG_PATH init --initial-branch=main && git -C $WORG_PATH remote add origin $WORG_REPO && git -C $WORG_PATH fetch origin $WORG_VERSION && git -C $WORG_PATH checkout FETCH_HEAD
+
+
+FROM tester as foreign-document-test
+RUN apk add --no-cache bash coreutils
+RUN mkdir /foreign_documents
+COPY --from=foreign-document-gather /foreign_documents/howardabrams /foreign_documents/howardabrams
+COPY --from=foreign-document-gather /foreign_documents/doomemacs /foreign_documents/doomemacs
+COPY --from=foreign-document-gather /foreign_documents/worg /foreign_documents/worg
+COPY --from=build-org-mode /root/org-mode /foreign_documents/org-mode
+COPY --from=build-emacs /root/emacs /foreign_documents/emacs
+COPY foreign_document_test_entrypoint.sh /entrypoint.sh
+RUN chmod +x /entrypoint.sh
+ENTRYPOINT ["/entrypoint.sh"]

docker/organic_test/Makefile

@@ -6,7 +6,11 @@ all: build push
 
 .PHONY: build
 build:
-	docker build -t $(IMAGE_NAME) -f Dockerfile ../../
+	docker build -t $(IMAGE_NAME) -f Dockerfile --target tester .
+
+.PHONY: build_foreign_document_test
+build_foreign_document_test:
+	docker build -t $(IMAGE_NAME)-foreign-document -f Dockerfile --target foreign-document-test .
 
 .PHONY: push
 push:
@@ -29,8 +33,12 @@ endif
 
 .PHONY: run
 run: build
-	docker run --rm --init -v "$$(readlink -f ../../):/source:ro" --workdir=/source --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target $(IMAGE_NAME) --no-default-features --features compare --no-fail-fast --lib --test test_loader
+	docker run --rm --init --read-only --mount type=tmpfs,destination=/tmp -v "$$(readlink -f ../../):/source:ro" --workdir=/source --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target $(IMAGE_NAME) --no-default-features --features compare --no-fail-fast --lib --test test_loader
 
 .PHONY: shell
 shell: build
-	docker run --rm -i -t --entrypoint /bin/sh -v "$$(readlink -f ../../):/source:ro" --workdir=/source --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target $(IMAGE_NAME)
+	docker run --rm -i -t --entrypoint /bin/sh --mount type=tmpfs,destination=/tmp -v "$$(readlink -f ../../):/source:ro" --workdir=/source --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target $(IMAGE_NAME)
+
+.PHONY: run_foreign_document_test
+run_foreign_document_test: build_foreign_document_test
+	docker run --rm --init --read-only --mount type=tmpfs,destination=/tmp -v "$$(readlink -f ../../):/source:ro" --workdir=/source --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target $(IMAGE_NAME)-foreign-document

docker/organic_test/foreign_document_test_entrypoint.sh

@@ -0,0 +1,149 @@
+#!/usr/bin/env bash
+#
+# Run the Organic compare script against a series of documents sourced from exterior places.
+set -euo pipefail
+IFS=$'\n\t'
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
+
+REALPATH=$(command -v uu-realpath || command -v realpath)
+
+function log {
+    (>&2 echo "${@}")
+}
+
+function die {
+    local status_code="$1"
+    shift
+    (>&2 echo "${@}")
+    exit "$status_code"
+}
+
+function main {
+    cargo build --no-default-features --features compare --profile release-lto
+    if [ "${CARGO_TARGET_DIR:-}" = "" ]; then
+        CARGO_TARGET_DIR=$(realpath target/)
+    fi
+    PARSE="${CARGO_TARGET_DIR}/release-lto/compare"
+
+    local all_status=0
+    set +e
+
+    (run_compare_function "org-mode" compare_all_org_document "/foreign_documents/org-mode")
+    if [ "$?" -ne 0 ]; then all_status=1; fi
+    (run_compare_function "emacs" compare_all_org_document "/foreign_documents/emacs")
+    if [ "$?" -ne 0 ]; then all_status=1; fi
+    (run_compare_function "worg" compare_all_org_document "/foreign_documents/worg")
+    if [ "$?" -ne 0 ]; then all_status=1; fi
+    (run_compare_function "howard_abrams" compare_howard_abrams)
+    if [ "$?" -ne 0 ]; then all_status=1; fi
+    (run_compare_function "doomemacs" compare_all_org_document "/foreign_documents/doomemacs")
+    if [ "$?" -ne 0 ]; then all_status=1; fi
+
+    set -e
+    if [ "$all_status" -ne 0 ]; then
+        red_text "Some tests failed."
+    else
+        green_text "All tests passed."
+    fi
+    return "$all_status"
+}
+
+function green_text {
+    (IFS=' '; printf '\x1b[38;2;0;255;0m%s\x1b[0m' "${*}")
+}
+
+function red_text {
+    (IFS=' '; printf '\x1b[38;2;255;0;0m%s\x1b[0m' "${*}")
+}
+
+function yellow_text {
+    (IFS=' '; printf '\x1b[38;2;255;255;0m%s\x1b[0m' "${*}")
+}
+
+function indent {
+    local depth="$1"
+    local scaled_depth=$((depth * 2))
+    shift 1
+    local prefix
+    prefix=$(printf -- "%${scaled_depth}s")
+    while read -r l; do
+        (IFS=' '; printf -- '%s%s\n' "$prefix" "$l")
+    done
+}
+
+function run_compare_function {
+    local name="$1"
+    local stdoutput
+    shift 1
+    set +e
+    stdoutput=$("${@}")
+    local status=$?
+    set -e
+    if [ "$status" -eq 0 ]; then
+        echo "$(green_text "GOOD")  $name"
+        indent 1 <<<"$stdoutput"
+    else
+        echo "$(red_text "FAIL")  $name"
+        indent 1 <<<"$stdoutput"
+        return 1
+    fi
+}
+
+function compare_all_org_document {
+    local root_dir="$1"
+    local target_document
+    local all_status=0
+    while read target_document; do
+        local relative_path
+        relative_path=$($REALPATH --relative-to "$root_dir" "$target_document")
+        set +e
+        (run_compare "$relative_path" "$target_document")
+        if [ "$?" -ne 0 ]; then all_status=1; fi
+        set -e
+    done<<<"$(find "$root_dir" -type f -iname '*.org' | sort)"
+    return "$all_status"
+}
+
+function run_compare {
+    local name="$1"
+    local target_document="$2"
+    set +e
+    ($PARSE "$target_document" &> /dev/null)
+    local status=$?
+    set -e
+    if [ "$status" -eq 0 ]; then
+        echo "$(green_text "GOOD")  $name"
+    else
+        echo "$(red_text "FAIL")  $name"
+        return 1
+    fi
+}
+
+function compare_howard_abrams {
+    local all_status=0
+    set +e
+
+    (run_compare_function "dot-files" compare_all_org_document "/foreign_documents/howardabrams/dot-files")
+    if [ "$?" -ne 0 ]; then all_status=1; fi
+    (run_compare_function "hamacs" compare_all_org_document "/foreign_documents/howardabrams/hamacs")
+    if [ "$?" -ne 0 ]; then all_status=1; fi
+    (run_compare_function "demo-it" compare_all_org_document "/foreign_documents/howardabrams/demo-it")
+    if [ "$?" -ne 0 ]; then all_status=1; fi
+    (run_compare_function "magit-demo" compare_all_org_document "/foreign_documents/howardabrams/magit-demo")
+    if [ "$?" -ne 0 ]; then all_status=1; fi
+    (run_compare_function "pdx-emacs-hackers" compare_all_org_document "/foreign_documents/howardabrams/pdx-emacs-hackers")
+    if [ "$?" -ne 0 ]; then all_status=1; fi
+    (run_compare_function "flora-simulator" compare_all_org_document "/foreign_documents/howardabrams/flora-simulator")
+    if [ "$?" -ne 0 ]; then all_status=1; fi
+    (run_compare_function "literate-devops-demo" compare_all_org_document "/foreign_documents/howardabrams/literate-devops-demo")
+    if [ "$?" -ne 0 ]; then all_status=1; fi
+    (run_compare_function "clojure-yesql-xp" compare_all_org_document "/foreign_documents/howardabrams/clojure-yesql-xp")
+    if [ "$?" -ne 0 ]; then all_status=1; fi
+    (run_compare_function "veep" compare_all_org_document "/foreign_documents/howardabrams/veep")
+    if [ "$?" -ne 0 ]; then all_status=1; fi
+
+    set -e
+    return "$all_status"
+}
+
+main "${@}"

notes/optimization_ideas.org

@@ -25,3 +25,4 @@ This could significantly reduce our calls to exit matchers.
 I think targets would break this.
 
 The exit matchers are already implicitly building this behavior since they should all exit very early when the starting character is wrong. Putting this logic in a centralized place, far away from where those characters are actually going to be used, is unfortunate for readability.
+** Use exit matcher to cut off trailing whitespace instead of re-matching in plain lists.

org_mode_samples/README.org

@@ -0,0 +1 @@
+This folder contains org-mode documents that get automatically included as tests using build.rs.

org_mode_samples/greater_element/dynamic_block/no_closing_colon.org

@@ -0,0 +1,3 @@
+#+BEGIN: timestamp :format "%Y-%m-%d %H:%M"
+
+#+END

org_mode_samples/greater_element/footnote_definition/empty_space_before_and_after_content.org

@@ -0,0 +1,8 @@
+* Footnotes
+
+[fn:1]
+
+#+BEGIN_EXAMPLE
+baz
+#+END_EXAMPLE
+

org_mode_samples/greater_element/greater_block/deeply_nested.org

@@ -0,0 +1,18 @@
+#+begin_defun
+foo
+#+begin_lorem
+,#+begin_center
+bar
+,#+end_center
+ipsum
+#+end_lorem
+baz
+#+end_defun
+
+#+begin_center
+#+begin_quote
+#+begin_center
+lorem
+#+end_center
+#+end_quote
+#+end_center

org_mode_samples/greater_element/greater_block/nested_special_block.org

@@ -0,0 +1,12 @@
+#+begin_defun
+foo
+#+begin_lorem
+ipsum
+#+end_lorem
+bar
+#+begin_center
+#+begin_quote
+baz
+#+end_quote
+#+end_center
+#+end_defun

org_mode_samples/greater_element/greater_block/quote_block_with_leading_blank_line.org

@@ -0,0 +1,5 @@
+#+begin_quote
+
+foo
+
+#+end_quote

org_mode_samples/greater_element/greater_block/special_block.org

@@ -0,0 +1,5 @@
+#+begin_defun
+foo
+
+{{{bar(baz)}}}
+#+end_defun

org_mode_samples/greater_element/plain_list/alphabetical_bullets.org

@@ -0,0 +1,3 @@
+# These are only allowed by configuring org-list-allow-alphabetical which the automated tests are not currently set up to do, so this will parse as a paragraph:
+a. foo
+b. bar

org_mode_samples/greater_element/plain_list/counter_set.org

@@ -0,0 +1,2 @@
+3. [@3] foo
+4. bar

org_mode_samples/greater_element/plain_list/description_list_empty_value.org

@@ -0,0 +1,6 @@
+- foo ::
+
+- bar ::
+
+
+baz

org_mode_samples/greater_element/plain_list/description_list_object_key.org

@@ -0,0 +1,2 @@
+- {{{foo(bar)}}} :: baz
+- =foo=          :: bar

org_mode_samples/greater_element/plain_list/description_list_tabs.org

@@ -0,0 +1,3 @@
+- foo    	:: bar
+- foo	    	:: bar
+- foo	    	::	bar

org_mode_samples/greater_element/plain_list/description_list_with_double_colon_in_tag.org

@@ -0,0 +1,2 @@
+- =foo :: bar= :: baz
+- lorem :: ipsum :: dolar

org_mode_samples/greater_element/plain_list/empty_list_item.org

@@ -1,3 +1,5 @@
 1.
 2.
 3.
+
+* headline

org_mode_samples/greater_element/plain_list/mixed_types.org

@@ -0,0 +1,3 @@
+1. foo
+- bar
+- lorem :: ipsum

org_mode_samples/greater_element/plain_list/ordered_list_with_fake_tag.org

@@ -0,0 +1,2 @@
+# Since this is an ordered list, the text before the " :: " is NOT parsed as a tag.
+1. foo :: bar

org_mode_samples/greater_element/plain_list/trailing_whitespace_eof.org

@@ -0,0 +1,2 @@
+- foo
+

org_mode_samples/greater_element/property_drawer/key_with_colon.org

@@ -0,0 +1,6 @@
+* Overwrite
+  :PROPERTIES:
+  :header-args: :var foo="lorem"
+  :header-args:emacs-lisp: :var bar="ipsum"
+  :header-args:emacs-lisp+: :results silent :var baz=7
+  :END:

org_mode_samples/greater_element/table/align_unaligned_table.org

@@ -0,0 +1,6 @@
+# The STARTUP directive here instructs org-mode to align tables which emacs normally does when opening the file. Since Organic is solely a parser, we have no business editing the org-mode document so Organic does not handle aligning tables, so in order for this test to pass, we have to avoid that behavior in Emacs.
+#+STARTUP: align
+
+|foo|bar|
+|-
+|lorem|ipsum|

org_mode_samples/greater_element/table/cells_with_objects.org

@@ -0,0 +1,6 @@
+src_elisp{(bar)}
+*src_elisp{(bar)}*
+
+| foo *bar* |
+| foo src_elisp{(bar)} |
+| foo *src_elisp{(bar)}* |

org_mode_samples/greater_element/table/empty_formula.org

@@ -0,0 +1,4 @@
+| Name | Value |
+|------+-------|
+| foo  | bar   |
+#+tblfm:

org_mode_samples/greater_element/table/with_formulas.org

@@ -0,0 +1,8 @@
+| Name | Price | Quantity | Total |
+|------+-------+----------+-------|
+| foo  |     7 |        4 |    28 |
+| bar  |   3.5 |        3 |  10.5 |
+|------+-------+----------+-------|
+|      |       |        7 |  38.5 |
+#+tblfm: $4=$2*$3::@>$4=vsum(@2..@-1)
+#+tblfm: @>$3=vsum(@2..@-1)

org_mode_samples/lesser_element/diary_sexp/not_real_sexp.org

@@ -0,0 +1,6 @@
+%%(foo
+)
+
+%%(bar    ;  baz
+
+lorem

org_mode_samples/lesser_element/diary_sexp/with_comment_at_end_of_line.org

@@ -0,0 +1 @@
+%%(foo bar)    ;    baz

org_mode_samples/lesser_element/fixed_width_area/tab_instead_of_space.org

@@ -0,0 +1,2 @@
+# Fixed width areas must begin with colon followed by a space, not a tab, so this is not a fixed width area.
+:	foo

org_mode_samples/lesser_element/keyword/affiliated_keywords_short_version.org

@@ -0,0 +1,7 @@
+# This test is to prove that the parser works with affiliated keywords that have both a shorter and longer version.
+
+#+results:
+#+result:
+#+begin_latex
+\foo
+#+end_latex

org_mode_samples/lesser_element/keyword/babel_call.org

@@ -0,0 +1 @@
+#+call: foo(bar="baz")

org_mode_samples/lesser_element/keyword/keyword_with_colon_in_key.org

@@ -0,0 +1 @@
+#+title:foo:bar: baz: lorem: ipsum

org_mode_samples/lesser_element/lesser_block/src_empty.org

@@ -0,0 +1,2 @@
+#+begin_src
+#+end_src

org_mode_samples/lesser_element/lesser_block/src_with_space_after_end.org

@@ -0,0 +1,4 @@
+# There are trailing spaces after the begin and end src lines
+#+begin_src    
+  echo "this is a source block."
+#+end_src    

org_mode_samples/object/footnote_reference/nested_footnote_references.org

@@ -0,0 +1,3 @@
+*[fn:: /abcdef[fn::ghijklmnopqrstuvw]xyz/ r]*
+
+*[fn:: /abcdef[fn::ghijk *lmnopq* rstuvw]xyz/ r]*

org_mode_samples/object/plain_link/with_parenthesis.org

@@ -0,0 +1,11 @@
+# Should be a link:
+https://en.wikipedia.org/wiki/Shebang_(Unix)
+
+# No closing parenthesis, so link ends at underscore.
+https://en.wikipedia.org/wiki/Shebang_(Unix
+
+# Parenthesis only allowed to depth of 2 so link ends at underscore.
+https://en.wikipedia.org/wiki/Shebang_(((Unix)))
+
+# Even though they eventually become balanced, we hit negative parenthesis depth so link ends at )
+https://en.wikipedia.org/wiki/Shebang)Unix(

org_mode_samples/object/plain_link/with_trailing_whitespace.org

@@ -0,0 +1 @@
+mailto:foo@bar.baz      .

org_mode_samples/object/radio_link/different_case.org

@@ -0,0 +1,3 @@
+<<<Foo Bar Baz>>>
+
+foo bar baz

org_mode_samples/object/radio_link/different_whitespace.org

@@ -0,0 +1,6 @@
+<<<foo bar baz>>>
+
+
+foo
+bar
+baz

org_mode_samples/object/regular_link/elisp.org

@@ -0,0 +1 @@
+[[elisp:(local-set-key "\M-\x" 'foo-bar-baz)]]

org_mode_samples/object/regular_link/with_parenthesis.org

@@ -0,0 +1 @@
+[[https://en.wikipedia.org/wiki/Shebang_(Unix)]]

org_mode_samples/object/regular_link/wrapped_with_brackets.org

@@ -0,0 +1 @@
+[[[http://foo.bar/baz][lorem]]]

org_mode_samples/object/statistics_cookie/empty.org

@@ -0,0 +1,4 @@
+[/]
+[/2]
+[3/]
+[%]

org_mode_samples/object/subscript_and_superscript/options_require_braces.org

@@ -0,0 +1,7 @@
+# Even though *exporting* honors the setting to require braces for subscript/superscript, the official org-mode parser still parses subscripts and superscripts.
+
+#+OPTIONS:    ^:{}
+foo_this isn't a subscript when exported due to lack of braces (but its still a subscript during parsing)
+
+
+bar_{this is a subscript}

org_mode_samples/object/subscript_and_superscript/with_parenthesis.org

@@ -0,0 +1,13 @@
+foo_(bar)
+
+foo_(b(ar)
+
+foo_(b{ar)
+
+foo_{b(ar}
+
+foo_(b(a)r)
+
+foo_b(a)r
+
+foo_(b+ar)

org_mode_samples/object/text_markup/double_star.org

@@ -0,0 +1 @@
+foo ** bar ** baz

org_mode_samples/object/text_markup/double_tilde.org

@@ -0,0 +1 @@
+foo ~~ bar ~~ baz

org_mode_samples/object/text_markup/target_substring.org

@@ -0,0 +1,4 @@
+# Since "foos" has an extra "s", this does not match the target.
+the foos bar
+
+The <<<foo>>> and stuff.

org_mode_samples/object/text_markup/verbatim_with_equals_inside.org

@@ -0,0 +1,4 @@
+foo ==>bar=.
+
+# This uses a zero-width space to escape the equals signs to make the verbatim not end.
+=lorem =​= ipsum=

org_mode_samples/sections_and_headings/comment_heading.org

@@ -0,0 +1,2 @@
+* TODO [#A] COMMENT foo bar
+baz

org_mode_samples/sections_and_headings/empty_heading.org

@@ -0,0 +1,2 @@
+* DONE
+* 

org_mode_samples/sections_and_headings/fast_access_todo_states.org

@@ -0,0 +1,6 @@
+#+TODO: TODO(t) INPROGRESS(i/!) | DONE(d!) CANCELED(c@/!)
+# !  : Log changes leading to this state.
+# @  : Log changes leading to this state and prompt for a comment to include.
+# /! : Log changes leaving this state if and only if to a state that does not log. This can be combined with the above like WAIT(w!/!) or DELAYED(d@/!)
+* INPROGRESS
+- State "TODO"       from "INPROGRESS" [2023-09-14 Thu 02:13]

org_mode_samples/sections_and_headings/odd_level_depth.org

@@ -0,0 +1,8 @@
+#+STARTUP: odd
+* Foo
+***** Bar
+* Baz
+*** Lorem
+* Ipsum
+**** Dolar
+***** Cat

org_mode_samples/sections_and_headings/section_with_planning_and_whitespace.org

@@ -0,0 +1,4 @@
+* DONE foo
+   DEADLINE: <2023-09-08 Fri>
+
+* DONE bar

org_mode_samples/sections_and_headings/statistics_cookie_with_space.org

@@ -0,0 +1 @@
+* [0/4] foo

scripts/callgrind.bash

@@ -4,10 +4,10 @@ set -euo pipefail
 IFS=$'\n\t'
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
 
-cd "$DIR/../"
 
-RUSTFLAGS="-C opt-level=0" cargo build --no-default-features
-valgrind --tool=callgrind --callgrind-out-file=callgrind.out target/debug/compare
+
+(cd "$DIR/../" && RUSTFLAGS="-C opt-level=0" cargo build --no-default-features)
+valgrind --tool=callgrind --callgrind-out-file="$DIR/../callgrind.out" "$DIR/../target/debug/parse" "${@}"
 
 echo "You probably want to run:"
-echo "callgrind_annotate --auto=yes callgrind.out"
+echo "callgrind_annotate --auto=yes '$DIR/../callgrind.out'"

scripts/perf.bash

@@ -6,8 +6,6 @@ DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
 
 : ${PROFILE:="perf"}
 
-cd "$DIR/../"
-
 function main {
     local additional_flags=()
     if [ "$PROFILE" = "dev" ] || [ "$PROFILE" = "debug" ]; then
@@ -15,12 +13,12 @@ function main {
     else
         additional_flags+=(--profile "$PROFILE")
     fi
-    cargo build --no-default-features "${additional_flags[@]}"
-    perf record --freq=2000 --call-graph dwarf --output=perf.data target/${PROFILE}/compare
+    (cd "$DIR/../" && cargo build --no-default-features "${additional_flags[@]}")
+    perf record --freq=2000 --call-graph dwarf --output="$DIR/../perf.data" "$DIR/../target/${PROFILE}/parse" "${@}"
 
     # Convert to a format firefox will read
     # flags to consider --show-info
-    perf script -F +pid --input perf.data > perf.firefox
+    perf script -F +pid --input "$DIR/../perf.data" > "$DIR/../perf.firefox"
 
     echo "You probably want to go to https://profiler.firefox.com/"
     echo "Either that or run hotspot"

scripts/run_docker_compare.bash

@@ -8,15 +8,29 @@ DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
 : ${TRACE:="NO"} # or YES to send traces to jaeger
 : ${BACKTRACE:="NO"} # or YES to print a rust backtrace when panicking
 : ${NO_COLOR:=""} # Set to anything to disable color output
+: ${PROFILE:="debug"}
 
-
-cd "$DIR/../"
 REALPATH=$(command -v uu-realpath || command -v realpath)
 MAKE=$(command -v gmake || command -v make)
 
+############## Setup #########################
+
+function die {
+    local status_code="$1"
+    shift
+    (>&2 echo "${@}")
+    exit "$status_code"
+}
+
+function log {
+    (>&2 echo "${@}")
+}
+
+############## Program #########################
+
 function main {
     build_container
-    launch_container
+    launch_container "${@}"
 }
 
 function build_container {
@@ -25,7 +39,6 @@ function build_container {
 
 function launch_container {
     local additional_flags=()
-    local additional_args=()
     local features=(compare)
 
     if [ "$NO_COLOR" != "" ]; then
@@ -39,10 +52,8 @@ function launch_container {
     fi
 
     if [ "$SHELL" != "YES" ]; then
-        local features_joined=$(IFS=","; echo "${features[*]}")
-        additional_args+=(cargo run --no-default-features --features "$features_joined")
+        additional_flags+=(--read-only)
     else
-        additional_args+=(/bin/sh)
         additional_flags+=(-t)
     fi
 
@@ -50,7 +61,51 @@ function launch_container {
         additional_flags+=(--env RUST_BACKTRACE=full)
     fi
 
-    docker run "${additional_flags[@]}" --init --rm -i -v "$($REALPATH ./):/source:ro" --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target -w /source --entrypoint "" organic-test "${additional_args[@]}"
+    if [ "$SHELL" = "YES" ]; then
+        exec docker run "${additional_flags[@]}" --init --rm -i --mount type=tmpfs,destination=/tmp -v "/:/input:ro" -v "$($REALPATH "$DIR/../"):/source:ro" --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target -w /source --entrypoint "" organic-test /bin/sh
+    fi
+
+    local features_joined
+    features_joined=$(IFS=","; echo "${features[*]}")
+
+    local build_flags=()
+    if [ "$PROFILE" = "dev" ] || [ "$PROFILE" = "debug" ]; then
+        PROFILE="debug"
+    else
+        build_flags+=(--profile "$PROFILE")
+    fi
+
+
+    if [ $# -gt 0 ]; then
+        # If we passed in args, we need to forward them along
+        for path in "${@}"; do
+            local full_path
+            full_path=$($REALPATH "$path")
+            init_script=$(cat <<EOF
+set -euo pipefail
+IFS=\$'\n\t'
+
+cargo build --bin compare --no-default-features --features "$features_joined" ${build_flags[@]}
+exec /target/${PROFILE}/compare "/input${full_path}"
+EOF
+                       )
+            docker run "${additional_flags[@]}" --init --rm -i --mount type=tmpfs,destination=/tmp -v "/:/input:ro"  -v "$($REALPATH "$DIR/../"):/source:ro" --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target -w /source --entrypoint "" organic-test sh -c "$init_script"
+        done
+    else
+        local current_directory init_script
+        current_directory=$(pwd)
+        init_script=$(cat <<EOF
+set -euo pipefail
+IFS=\$'\n\t'
+
+cargo build --bin compare --no-default-features --features "$features_joined" ${build_flags[@]}
+cd /input${current_directory}
+exec /target/${PROFILE}/compare
+EOF
+                       )
+
+        docker run "${additional_flags[@]}" --init --rm -i --mount type=tmpfs,destination=/tmp -v "/:/input:ro" -v "$($REALPATH "$DIR/../"):/source:ro" --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target -w /source --entrypoint "" organic-test sh -c "$init_script"
+    fi
 }
 
 main "${@}"

scripts/run_docker_compare_bisect.bash

@@ -0,0 +1,72 @@
+#!/usr/bin/env bash
+#
+# Bisect parsing a file at various line cut-off points to see which line causes the parse to differ from emacs.
+set -euo pipefail
+IFS=$'\n\t'
+DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
+
+REALPATH=$(command -v uu-realpath || command -v realpath)
+
+############## Setup #########################
+
+function die {
+    local status_code="$1"
+    shift
+    (>&2 echo "${@}")
+    exit "$status_code"
+}
+
+function log {
+    (>&2 echo "${@}")
+}
+
+############## Program #########################
+
+function main {
+    local target_full_path
+    target_full_path=$($REALPATH "$1")
+    SOURCE_FOLDER=$(dirname "$target_full_path")
+    TARGET_DOCUMENT=$(basename "$target_full_path")
+
+
+    local good=0
+    local bad
+    bad=$(wc -l "$SOURCE_FOLDER/$TARGET_DOCUMENT" | awk '{print $1}')
+
+    set +e
+    (run_parse "$bad")
+    local status=$?
+    set -e
+    if [ $status -eq 0 ]; then
+        log "Entire file passes."
+        exit 0
+    fi
+
+    while [[ "$((bad - good))" -gt 1 ]]; do
+        local next_line=$((((bad - good) / 2) + good))
+        log "Testing line $next_line"
+        set +e
+        run_parse "$next_line" &> /dev/null
+        local status=$?
+        set -e
+        if [ $status -eq 0 ]; then
+            good="$next_line"
+            log "Line $next_line good"
+        else
+            bad="$next_line"
+            log "Line $next_line bad"
+        fi
+    done
+    echo "Bad line: $bad"
+}
+
+function run_parse {
+    local lines="$1"
+
+    cd "$SOURCE_FOLDER"
+    head -n "$lines" "$SOURCE_FOLDER/$TARGET_DOCUMENT" | PROFILE=release-lto "${DIR}/run_docker_compare.bash"
+    local status=$?
+    return "$status"
+}
+
+main "${@}"

scripts/run_docker_integration_test.bash

@@ -6,7 +6,6 @@ DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
 
 : ${NO_COLOR:=""} # Set to anything to disable color output
 
-cd "$DIR/../"
 REALPATH=$(command -v uu-realpath || command -v realpath)
 MAKE=$(command -v gmake || command -v make)
 
@@ -33,7 +32,7 @@ function get_test_names {
             local test_file_full_path=$($REALPATH "$test_file")
             local relative_to_samples=$($REALPATH --relative-to "$samples_dir" "$test_file_full_path")
             local without_extension="${relative_to_samples%.org}"
-            echo "${without_extension/\//_}" | tr '[:upper:]' '[:lower:]'
+            echo "autogen_${without_extension//\//_}" | tr '[:upper:]' '[:lower:]'
         else
             echo "$test_file" | tr '[:upper:]' '[:lower:]'
         fi
@@ -56,7 +55,7 @@ cargo test --no-default-features --features compare --no-fail-fast --lib --test
 EOF
           )
 
-    docker run "${additional_flags[@]}" --init --rm -v "$($REALPATH ./):/source:ro" --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target -w /source --entrypoint "" organic-test sh -c "$init_script"
+    docker run "${additional_flags[@]}" --init --rm --read-only --mount type=tmpfs,destination=/tmp -v "$($REALPATH "$DIR/../"):/source:ro" --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target -w /source --entrypoint "" organic-test sh -c "$init_script"
 }
 
 

scripts/run_integration_test.bash

@@ -4,7 +4,6 @@ set -euo pipefail
 IFS=$'\n\t'
 DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
 
-cd "$DIR/../"
 REALPATH=$(command -v uu-realpath || command -v realpath)
 
 function main {
@@ -12,7 +11,7 @@ function main {
 
     local test
     while read test; do
-        cargo test --no-default-features --features compare --no-fail-fast --test test_loader "$test" -- --show-output
+        (cd "$DIR/../" && cargo test --no-default-features --features compare --no-fail-fast --test test_loader "$test" -- --show-output)
     done<<<"$test_names"
 }
 
@@ -25,7 +24,7 @@ function get_test_names {
             local test_file_full_path=$($REALPATH "$test_file")
             local relative_to_samples=$($REALPATH --relative-to "$samples_dir" "$test_file_full_path")
             local without_extension="${relative_to_samples%.org}"
-            echo "${without_extension/\//_}" | tr '[:upper:]' '[:lower:]'
+            echo "${without_extension//\//_}" | tr '[:upper:]' '[:lower:]'
         else
             echo "$test_file" | tr '[:upper:]' '[:lower:]'
         fi

scripts/time_parse.bash

@@ -7,8 +7,6 @@ DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
 
 : ${PROFILE:="release-lto"}
 
-cd "$DIR/../"
-
 function main {
     local additional_flags=()
     if [ "$PROFILE" = "dev" ] || [ "$PROFILE" = "debug" ]; then
@@ -16,8 +14,8 @@ function main {
     else
         additional_flags+=(--profile "$PROFILE")
     fi
-    cargo build --no-default-features "${additional_flags[@]}"
-    time ./target/${PROFILE}/compare
+    (cd "$DIR/../" && cargo build --no-default-features "${additional_flags[@]}")
+    time "$DIR/../target/${PROFILE}/parse" "${@}"
 }
 
 main "${@}"

src/bin_compare.rs

@@ -0,0 +1,52 @@
+#![feature(round_char_boundary)]
+#![feature(exact_size_is_empty)]
+use std::io::Read;
+
+use organic::compare::run_anonymous_compare;
+use organic::compare::run_compare_on_file;
+
+#[cfg(feature = "tracing")]
+use crate::init_tracing::init_telemetry;
+#[cfg(feature = "tracing")]
+use crate::init_tracing::shutdown_telemetry;
+#[cfg(feature = "tracing")]
+mod init_tracing;
+
+#[cfg(not(feature = "tracing"))]
+fn main() -> Result<(), Box<dyn std::error::Error>> {
+    main_body()
+}
+
+#[cfg(feature = "tracing")]
+fn main() -> Result<(), Box<dyn std::error::Error>> {
+    let rt = tokio::runtime::Runtime::new()?;
+    let result = rt.block_on(async {
+        init_telemetry()?;
+        let main_body_result = main_body();
+        shutdown_telemetry()?;
+        main_body_result
+    });
+    result
+}
+
+#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
+fn main_body() -> Result<(), Box<dyn std::error::Error>> {
+    let args = std::env::args().skip(1);
+    if args.is_empty() {
+        let org_contents = read_stdin_to_string()?;
+        run_anonymous_compare(org_contents)
+    } else {
+        for arg in args {
+            run_compare_on_file(arg)?
+        }
+        Ok(())
+    }
+}
+
+fn read_stdin_to_string() -> Result<String, Box<dyn std::error::Error>> {
+    let mut stdin_contents = String::new();
+    std::io::stdin()
+        .lock()
+        .read_to_string(&mut stdin_contents)?;
+    Ok(stdin_contents)
+}

src/compare/compare.rs

@@ -0,0 +1,77 @@
+use std::path::Path;
+
+use crate::compare::diff::compare_document;
+use crate::compare::parse::emacs_parse_anonymous_org_document;
+use crate::compare::parse::emacs_parse_file_org_document;
+use crate::compare::parse::get_emacs_version;
+use crate::compare::parse::get_org_mode_version;
+use crate::compare::sexp::sexp;
+use crate::parser::parse;
+use crate::parser::parse_with_settings;
+use crate::GlobalSettings;
+use crate::LocalFileAccessInterface;
+
+pub fn run_anonymous_compare<P: AsRef<str>>(
+    org_contents: P,
+) -> Result<(), Box<dyn std::error::Error>> {
+    // TODO: This is a work-around to pretend that dos line endings do not exist. It would be better to handle the difference in line endings.
+    let org_contents = org_contents.as_ref().replace("\r\n", "\n");
+    let org_contents = org_contents.as_str();
+    eprintln!("Using emacs version: {}", get_emacs_version()?.trim());
+    eprintln!("Using org-mode version: {}", get_org_mode_version()?.trim());
+    let rust_parsed = parse(org_contents)?;
+    let org_sexp = emacs_parse_anonymous_org_document(org_contents)?;
+    let (_remaining, parsed_sexp) = sexp(org_sexp.as_str()).map_err(|e| e.to_string())?;
+
+    println!("{}\n\n\n", org_contents);
+    println!("{}", org_sexp);
+    println!("{:#?}", rust_parsed);
+
+    // We do the diffing after printing out both parsed forms in case the diffing panics
+    let diff_result = compare_document(&parsed_sexp, &rust_parsed)?;
+    diff_result.print(org_contents)?;
+
+    if diff_result.is_bad() {
+        Err("Diff results do not match.")?;
+    }
+
+    Ok(())
+}
+
+pub fn run_compare_on_file<P: AsRef<Path>>(org_path: P) -> Result<(), Box<dyn std::error::Error>> {
+    let org_path = org_path.as_ref();
+    eprintln!("Using emacs version: {}", get_emacs_version()?.trim());
+    eprintln!("Using org-mode version: {}", get_org_mode_version()?.trim());
+    let parent_directory = org_path
+        .parent()
+        .ok_or("Should be contained inside a directory.")?;
+    let org_contents = std::fs::read_to_string(org_path)?;
+    // TODO: This is a work-around to pretend that dos line endings do not exist. It would be better to handle the difference in line endings.
+    let org_contents = org_contents.replace("\r\n", "\n");
+    let org_contents = org_contents.as_str();
+    let file_access_interface = LocalFileAccessInterface {
+        working_directory: Some(parent_directory.to_path_buf()),
+    };
+    let global_settings = {
+        let mut global_settings = GlobalSettings::default();
+        global_settings.file_access = &file_access_interface;
+        global_settings
+    };
+    let rust_parsed = parse_with_settings(org_contents, &global_settings)?;
+    let org_sexp = emacs_parse_file_org_document(org_path)?;
+    let (_remaining, parsed_sexp) = sexp(org_sexp.as_str()).map_err(|e| e.to_string())?;
+
+    println!("{}\n\n\n", org_contents);
+    println!("{}", org_sexp);
+    println!("{:#?}", rust_parsed);
+
+    // We do the diffing after printing out both parsed forms in case the diffing panics
+    let diff_result = compare_document(&parsed_sexp, &rust_parsed)?;
+    diff_result.print(org_contents)?;
+
+    if diff_result.is_bad() {
+        Err("Diff results do not match.")?;
+    }
+
+    Ok(())
+}

src/compare/diff.rs

@@ -1,68 +1,73 @@
+use std::collections::BTreeSet;
 use std::collections::HashSet;
 
+use super::sexp::unquote;
+use super::sexp::Token;
 use super::util::assert_bounds;
 use super::util::assert_name;
 use super::util::get_property;
-use crate::parser::sexp::unquote;
-use crate::parser::sexp::Token;
-use crate::parser::AngleLink;
-use crate::parser::Bold;
-use crate::parser::Citation;
-use crate::parser::CitationReference;
-use crate::parser::Clock;
-use crate::parser::Code;
-use crate::parser::Comment;
-use crate::parser::CommentBlock;
-use crate::parser::DiarySexp;
-use crate::parser::Document;
-use crate::parser::DocumentElement;
-use crate::parser::Drawer;
-use crate::parser::DynamicBlock;
-use crate::parser::Element;
-use crate::parser::Entity;
-use crate::parser::ExampleBlock;
-use crate::parser::ExportBlock;
-use crate::parser::ExportSnippet;
-use crate::parser::FixedWidthArea;
-use crate::parser::FootnoteDefinition;
-use crate::parser::FootnoteReference;
-use crate::parser::GreaterBlock;
-use crate::parser::Heading;
-use crate::parser::HorizontalRule;
-use crate::parser::InlineBabelCall;
-use crate::parser::InlineSourceBlock;
-use crate::parser::Italic;
-use crate::parser::Keyword;
-use crate::parser::LatexEnvironment;
-use crate::parser::LatexFragment;
-use crate::parser::LineBreak;
-use crate::parser::Object;
-use crate::parser::OrgMacro;
-use crate::parser::Paragraph;
-use crate::parser::PlainLink;
-use crate::parser::PlainList;
-use crate::parser::PlainListItem;
-use crate::parser::PlainText;
-use crate::parser::Planning;
-use crate::parser::PropertyDrawer;
-use crate::parser::RadioLink;
-use crate::parser::RadioTarget;
-use crate::parser::RegularLink;
-use crate::parser::Section;
-use crate::parser::Source;
-use crate::parser::SrcBlock;
-use crate::parser::StatisticsCookie;
-use crate::parser::StrikeThrough;
-use crate::parser::Subscript;
-use crate::parser::Superscript;
-use crate::parser::Table;
-use crate::parser::TableCell;
-use crate::parser::TableRow;
-use crate::parser::Target;
-use crate::parser::Timestamp;
-use crate::parser::Underline;
-use crate::parser::Verbatim;
-use crate::parser::VerseBlock;
+use crate::types::AngleLink;
+use crate::types::Bold;
+use crate::types::CheckboxType;
+use crate::types::Citation;
+use crate::types::CitationReference;
+use crate::types::Clock;
+use crate::types::Code;
+use crate::types::Comment;
+use crate::types::CommentBlock;
+use crate::types::DiarySexp;
+use crate::types::Document;
+use crate::types::DocumentElement;
+use crate::types::Drawer;
+use crate::types::DynamicBlock;
+use crate::types::Element;
+use crate::types::Entity;
+use crate::types::ExampleBlock;
+use crate::types::ExportBlock;
+use crate::types::ExportSnippet;
+use crate::types::FixedWidthArea;
+use crate::types::FootnoteDefinition;
+use crate::types::FootnoteReference;
+use crate::types::GreaterBlock;
+use crate::types::Heading;
+use crate::types::HorizontalRule;
+use crate::types::InlineBabelCall;
+use crate::types::InlineSourceBlock;
+use crate::types::Italic;
+use crate::types::Keyword;
+use crate::types::LatexEnvironment;
+use crate::types::LatexFragment;
+use crate::types::LineBreak;
+use crate::types::NodeProperty;
+use crate::types::Object;
+use crate::types::OrgMacro;
+use crate::types::Paragraph;
+use crate::types::PlainLink;
+use crate::types::PlainList;
+use crate::types::PlainListItem;
+use crate::types::PlainText;
+use crate::types::Planning;
+use crate::types::PriorityCookie;
+use crate::types::PropertyDrawer;
+use crate::types::RadioLink;
+use crate::types::RadioTarget;
+use crate::types::RegularLink;
+use crate::types::Section;
+use crate::types::Source;
+use crate::types::SrcBlock;
+use crate::types::StatisticsCookie;
+use crate::types::StrikeThrough;
+use crate::types::Subscript;
+use crate::types::Superscript;
+use crate::types::Table;
+use crate::types::TableCell;
+use crate::types::TableRow;
+use crate::types::Target;
+use crate::types::Timestamp;
+use crate::types::TodoKeywordType;
+use crate::types::Underline;
+use crate::types::Verbatim;
+use crate::types::VerseBlock;
 
 #[derive(Debug)]
 pub enum DiffEntry<'s> {
@@ -82,7 +87,7 @@ pub struct DiffResult<'s> {
 }
 
 #[derive(Debug, PartialEq)]
-pub enum DiffStatus {
+enum DiffStatus {
     Good,
     Bad,
 }
@@ -305,6 +310,7 @@ fn compare_element<'s>(
         Element::FixedWidthArea(obj) => compare_fixed_width_area(source, emacs, obj),
         Element::HorizontalRule(obj) => compare_horizontal_rule(source, emacs, obj),
         Element::Keyword(obj) => compare_keyword(source, emacs, obj),
+        Element::BabelCall(obj) => compare_babel_call(source, emacs, obj),
         Element::LatexEnvironment(obj) => compare_latex_environment(source, emacs, obj),
     };
     match compare_result {
@@ -484,11 +490,11 @@ fn compare_heading<'s>(
     let level = get_property(emacs, ":level")?
         .ok_or("Level should not be nil")?
         .as_atom()?;
-    if rust.stars.to_string() != level {
+    if rust.level.to_string() != level {
         this_status = DiffStatus::Bad;
         message = Some(format!(
-            "Headline level do not much (emacs != rust): {} != {}",
-            level, rust.stars
+            "Headline level do not match (emacs != rust): {} != {}",
+            level, rust.level
         ))
     }
 
@@ -510,9 +516,9 @@ fn compare_heading<'s>(
         .map(Token::as_atom)
         .map_or(Ok(None), |r| r.map(Some))?
         .unwrap_or("nil");
-    match (todo_keyword, rust.todo_keyword, unquote(todo_keyword)) {
+    match (todo_keyword, &rust.todo_keyword, unquote(todo_keyword)) {
         ("nil", None, _) => {}
-        (_, Some(rust_todo), Ok(emacs_todo)) if emacs_todo == rust_todo => {}
+        (_, Some((_rust_todo_type, rust_todo)), Ok(emacs_todo)) if emacs_todo == *rust_todo => {}
         (emacs_todo, rust_todo, _) => {
             this_status = DiffStatus::Bad;
             message = Some(format!(
@@ -521,18 +527,98 @@ fn compare_heading<'s>(
             ));
         }
     };
+    // Compare todo-type
+    let todo_type = get_property(emacs, ":todo-type")?
+        .map(Token::as_atom)
+        .map_or(Ok(None), |r| r.map(Some))?
+        .unwrap_or("nil");
+    // todo-type is an unquoted string either todo, done, or nil
+    match (todo_type, &rust.todo_keyword) {
+        ("nil", None) => {}
+        ("todo", Some((TodoKeywordType::Todo, _))) => {}
+        ("done", Some((TodoKeywordType::Done, _))) => {}
+        (emacs_todo, rust_todo) => {
+            this_status = DiffStatus::Bad;
+            message = Some(format!(
+                "(emacs != rust) {:?} != {:?}",
+                emacs_todo, rust_todo
+            ));
+        }
+    };
 
     // Compare title
-    let title = get_property(emacs, ":title")?.ok_or("Missing :title attribute.")?;
-    let title_status = title
-        .as_list()?
-        .iter()
-        .zip(rust.title.iter())
-        .map(|(emacs_child, rust_child)| compare_object(source, emacs_child, rust_child))
-        .collect::<Result<Vec<_>, _>>()?;
-    child_status.push(artificial_diff_scope("title".to_owned(), title_status)?);
+    let title = get_property(emacs, ":title")?;
+    match (title, rust.title.len()) {
+        (None, 0) => {}
+        (None, _) => {
+            this_status = DiffStatus::Bad;
+            message = Some(format!(
+                "Titles do not match (emacs != rust): {:?} != {:?}",
+                title, rust.title
+            ))
+        }
+        (Some(title), _) => {
+            let title_status = title
+                .as_list()?
+                .iter()
+                .zip(rust.title.iter())
+                .map(|(emacs_child, rust_child)| compare_object(source, emacs_child, rust_child))
+                .collect::<Result<Vec<_>, _>>()?;
+            child_status.push(artificial_diff_scope("title".to_owned(), title_status)?);
+        }
+    };
 
-    // TODO: Compare todo-type, priority, :footnote-section-p, :archivedp, :commentedp
+    // Compare priority
+    let priority = get_property(emacs, ":priority")?;
+    match (priority, rust.priority_cookie) {
+        (None, None) => {}
+        (None, Some(_)) | (Some(_), None) => {
+            this_status = DiffStatus::Bad;
+            message = Some(format!(
+                "Priority cookie mismatch (emacs != rust) {:?} != {:?}",
+                priority, rust.priority_cookie
+            ));
+        }
+        (Some(emacs_priority_cookie), Some(rust_priority_cookie)) => {
+            let emacs_priority_cookie =
+                emacs_priority_cookie.as_atom()?.parse::<PriorityCookie>()?;
+            if emacs_priority_cookie != rust_priority_cookie {
+                this_status = DiffStatus::Bad;
+                message = Some(format!(
+                    "Priority cookie mismatch (emacs != rust) {:?} != {:?}",
+                    emacs_priority_cookie, rust_priority_cookie
+                ));
+            }
+        }
+    }
+
+    // Compare archived
+    let archived = get_property(emacs, ":archivedp")?;
+    match (archived, rust.is_archived) {
+        (None, true) | (Some(_), false) => {
+            this_status = DiffStatus::Bad;
+            message = Some(format!(
+                "archived mismatch (emacs != rust) {:?} != {:?}",
+                archived, rust.is_archived
+            ));
+        }
+        (None, false) | (Some(_), true) => {}
+    }
+
+    // Compare commented
+    let commented = get_property(emacs, ":commentedp")?;
+    match (commented, rust.is_comment) {
+        (None, true) | (Some(_), false) => {
+            this_status = DiffStatus::Bad;
+            message = Some(format!(
+                "commented mismatch (emacs != rust) {:?} != {:?}",
+                commented, rust.is_comment
+            ));
+        }
+        (None, false) | (Some(_), true) => {}
+    }
+
+    // TODO: Compare :footnote-section-p
 
     // Compare section
     let section_status = children
@@ -646,6 +732,10 @@ fn compare_plain_list<'s>(
         Ok(_) => {}
     };
 
+    // TODO compare :type
+    //
+    // :type is an unquoted atom of either descriptive, ordered, or unordered
+
     for (emacs_child, rust_child) in children.iter().skip(2).zip(rust.children.iter()) {
         child_status.push(compare_plain_list_item(source, emacs_child, rust_child)?);
     }
@@ -714,6 +804,27 @@ fn compare_plain_list_item<'s>(
         contents_status,
     )?);
 
+    // TODO: compare :bullet :counter :pre-blank
+
+    // Compare checkbox
+    let checkbox = get_property(emacs, ":checkbox")?
+        .map(Token::as_atom)
+        .map_or(Ok(None), |r| r.map(Some))?
+        .unwrap_or("nil");
+    match (checkbox, &rust.checkbox) {
+        ("nil", None) => {}
+        ("off", Some((CheckboxType::Off, _))) => {}
+        ("trans", Some((CheckboxType::Trans, _))) => {}
+        ("on", Some((CheckboxType::On, _))) => {}
+        _ => {
+            this_status = DiffStatus::Bad;
+            message = Some(format!(
+                "Checkbox mismatch (emacs != rust) {:?} != {:?}",
+                checkbox, rust.checkbox
+            ));
+        }
+    };
+
     Ok(DiffResult {
         status: this_status,
         name: emacs_name.to_owned(),
@@ -737,7 +848,7 @@ fn compare_greater_block<'s>(
     let emacs_name = match rust.name.to_lowercase().as_str() {
         "center" => "center-block",
         "quote" => "quote-block",
-        _ => todo!(),
+        _ => "special-block",
     };
     if assert_name(emacs, emacs_name).is_err() {
         this_status = DiffStatus::Bad;
@@ -787,6 +898,8 @@ fn compare_dynamic_block<'s>(
         Ok(_) => {}
     };
 
+    // TODO: Compare :block-name :arguments
+
     for (emacs_child, rust_child) in children.iter().skip(2).zip(rust.children.iter()) {
         child_status.push(compare_element(source, emacs_child, rust_child)?);
     }
@@ -914,7 +1027,7 @@ fn compare_property_drawer<'s>(
     rust: &'s PropertyDrawer<'s>,
 ) -> Result<DiffEntry<'s>, Box<dyn std::error::Error>> {
     let children = emacs.as_list()?;
-    let child_status = Vec::new();
+    let mut child_status = Vec::new();
     let mut this_status = DiffStatus::Good;
     let mut message = None;
     let emacs_name = "property-drawer";
@@ -930,9 +1043,8 @@ fn compare_property_drawer<'s>(
         Ok(_) => {}
     };
 
-    for (_emacs_child, _rust_child) in children.iter().skip(2).zip(rust.children.iter()) {
-        // TODO: What are node properties and are they the only legal child of property drawers?
-        // child_status.push(compare_element(source, emacs_child, rust_child)?);
+    for (emacs_child, rust_child) in children.iter().skip(2).zip(rust.children.iter()) {
+        child_status.push(compare_node_property(source, emacs_child, rust_child)?);
     }
 
     Ok(DiffResult {
@@ -946,6 +1058,40 @@ fn compare_property_drawer<'s>(
     .into())
 }
 
+fn compare_node_property<'s>(
+    source: &'s str,
+    emacs: &'s Token<'s>,
+    rust: &'s NodeProperty<'s>,
+) -> Result<DiffEntry<'s>, Box<dyn std::error::Error>> {
+    let child_status = Vec::new();
+    let mut this_status = DiffStatus::Good;
+    let mut message = None;
+    let emacs_name = "node-property";
+    if assert_name(emacs, emacs_name).is_err() {
+        this_status = DiffStatus::Bad;
+    }
+
+    match assert_bounds(source, emacs, rust) {
+        Err(err) => {
+            this_status = DiffStatus::Bad;
+            message = Some(err.to_string())
+        }
+        Ok(_) => {}
+    };
+
+    // TODO: Compare :key :value
+
+    Ok(DiffResult {
+        status: this_status,
+        name: emacs_name.to_owned(),
+        message,
+        children: child_status,
+        rust_source: rust.get_source(),
+        emacs_token: emacs,
+    }
+    .into())
+}
+
 fn compare_table<'s>(
     source: &'s str,
     emacs: &'s Token<'s>,
@@ -968,6 +1114,44 @@ fn compare_table<'s>(
         Ok(_) => {}
     };
 
+    // Compare formulas
+    //
+    // :tblfm is either nil or a list () filled with quoted strings containing the value for any tblfm keywords at the end of the table.
+    let emacs_formulas = get_property(emacs, ":tblfm")?;
+    if let Some(emacs_formulas) = emacs_formulas {
+        let emacs_formulas = emacs_formulas.as_list()?;
+        if emacs_formulas.len() != rust.formulas.len() {
+            this_status = DiffStatus::Bad;
+            message = Some(format!(
+                "Formulas do not match (emacs != rust): {:?} != {:?}",
+                emacs_formulas, rust.formulas
+            ))
+        } else {
+            let atoms = emacs_formulas
+                .into_iter()
+                .map(Token::as_atom)
+                .collect::<Result<Vec<_>, _>>()?;
+            let unquoted = atoms
+                .into_iter()
+                .map(unquote)
+                .collect::<Result<BTreeSet<_>, _>>()?;
+            for kw in &rust.formulas {
+                if !unquoted.contains(kw.value) {
+                    this_status = DiffStatus::Bad;
+                    message = Some(format!("Could not find formula in emacs: {}", kw.value))
+                }
+            }
+        }
+    } else {
+        if !rust.formulas.is_empty() {
+            this_status = DiffStatus::Bad;
+            message = Some(format!(
+                "Formulas do not match (emacs != rust): {:?} != {:?}",
+                emacs_formulas, rust.formulas
+            ))
+        }
+    }
+
     for (emacs_child, rust_child) in children.iter().skip(2).zip(rust.children.iter()) {
         child_status.push(compare_table_row(source, emacs_child, rust_child)?);
     }
@@ -1005,6 +1189,10 @@ fn compare_table_row<'s>(
         Ok(_) => {}
     };
 
+    // TODO: Compare :type
+    //
+    // :type is an unquoted atom of either standard or rule
+
     for (emacs_child, rust_child) in children.iter().skip(2).zip(rust.children.iter()) {
         child_status.push(compare_table_cell(source, emacs_child, rust_child)?);
     }
@@ -1203,6 +1391,8 @@ fn compare_src_block<'s>(
         Ok(_) => {}
     };
 
+    // TODO: Compare :language :switches :parameters :number-lines :preserve-indent :retain-labels :use-labels :label-fmt :value
+
     Ok(DiffResult {
         status: this_status,
         name: emacs_name.to_owned(),
@@ -1392,6 +1582,77 @@ fn compare_keyword<'s>(
         Ok(_) => {}
     };
 
+    let key = unquote(
+        get_property(emacs, ":key")?
+            .ok_or("Emacs keywords should have a :key")?
+            .as_atom()?,
+    )?;
+    if key != rust.key.to_uppercase() {
+        this_status = DiffStatus::Bad;
+        message = Some(format!(
+            "Mismatchs keyword keys (emacs != rust) {:?} != {:?}",
+            key, rust.key
+        ))
+    }
+    let value = unquote(
+        get_property(emacs, ":value")?
+            .ok_or("Emacs keywords should have a :value")?
+            .as_atom()?,
+    )?;
+    if value != rust.value {
+        this_status = DiffStatus::Bad;
+        message = Some(format!(
+            "Mismatchs keyword values (emacs != rust) {:?} != {:?}",
+            value, rust.value
+        ))
+    }
+
+    Ok(DiffResult {
+        status: this_status,
+        name: emacs_name.to_owned(),
+        message,
+        children: child_status,
+        rust_source: rust.get_source(),
+        emacs_token: emacs,
+    }
+    .into())
+}
+
+fn compare_babel_call<'s>(
+    source: &'s str,
+    emacs: &'s Token<'s>,
+    rust: &'s Keyword<'s>,
+) -> Result<DiffEntry<'s>, Box<dyn std::error::Error>> {
+    let child_status = Vec::new();
+    let mut this_status = DiffStatus::Good;
+    let mut message = None;
+    let emacs_name = "babel-call";
+    if assert_name(emacs, emacs_name).is_err() {
+        this_status = DiffStatus::Bad;
+    }
+
+    match assert_bounds(source, emacs, rust) {
+        Err(err) => {
+            this_status = DiffStatus::Bad;
+            message = Some(err.to_string())
+        }
+        Ok(_) => {}
+    };
+
+    // TODO: compare :call :inside-header :arguments :end-header
+    let value = unquote(
+        get_property(emacs, ":value")?
+            .ok_or("Emacs keywords should have a :value")?
+            .as_atom()?,
+    )?;
+    if value != rust.value {
+        this_status = DiffStatus::Bad;
+        message = Some(format!(
+            "Mismatchs keyword values (emacs != rust) {:?} != {:?}",
+            value, rust.value
+        ))
+    }
+
     Ok(DiffResult {
         status: this_status,
         name: emacs_name.to_owned(),
@@ -1457,7 +1718,7 @@ fn compare_plain_text<'s>(
         .as_atom()?
         .parse()?;
     let emacs_text_length = end_ind - start_ind;
-    if rust_source.len() != emacs_text_length {
+    if rust_source.chars().count() != emacs_text_length {
         this_status = DiffStatus::Bad;
         message = Some(format!(
             "(emacs len != rust len) {:?} != {:?}",
@@ -1691,6 +1952,8 @@ fn compare_regular_link<'s>(
         Ok(_) => {}
     };
 
+    // TODO: Compare :type :path :format :raw-link :application :search-option
+
     Ok(DiffResult {
         status: this_status,
         name: emacs_name.to_owned(),
@@ -2218,6 +2481,8 @@ fn compare_subscript<'s>(
         Ok(_) => {}
     };
 
+    // TODO compare :use-brackets-p
+
     Ok(DiffResult {
         status: this_status,
         name: emacs_name.to_owned(),
@@ -2249,6 +2514,8 @@ fn compare_superscript<'s>(
         Ok(_) => {}
     };
 
+    // TODO compare :use-brackets-p
+
     Ok(DiffResult {
         status: this_status,
         name: emacs_name.to_owned(),

src/compare/mod.rs

@@ -1,7 +1,7 @@
+mod compare;
 mod diff;
 mod parse;
+mod sexp;
 mod util;
-pub use diff::compare_document;
-pub use parse::emacs_parse_org_document;
-pub use parse::get_emacs_version;
-pub use parse::get_org_mode_version;
+pub use compare::run_anonymous_compare;
+pub use compare::run_compare_on_file;

src/compare/parse.rs

@@ -1,6 +1,9 @@
+use std::path::Path;
 use std::process::Command;
 
-pub fn emacs_parse_org_document<C>(file_contents: C) -> Result<String, Box<dyn std::error::Error>>
+pub fn emacs_parse_anonymous_org_document<C>(
+    file_contents: C,
+) -> Result<String, Box<dyn std::error::Error>>
 where
     C: AsRef<str>,
 {
@@ -8,6 +11,8 @@ where
     let elisp_script = format!(
         r#"(progn
      (erase-buffer)
+     (require 'org)
+     (defun org-table-align () t)
      (insert "{escaped_file_contents}")
      (org-mode)
      (message "%s" (pp-to-string (org-element-parse-buffer)))
@@ -15,14 +20,48 @@ where
         escaped_file_contents = escaped_file_contents
     );
     let mut cmd = Command::new("emacs");
-    let proc = cmd
+    let cmd = cmd
         .arg("-q")
         .arg("--no-site-file")
         .arg("--no-splash")
         .arg("--batch")
         .arg("--eval")
         .arg(elisp_script);
-    let out = proc.output()?;
+    let out = cmd.output()?;
+    out.status.exit_ok()?;
+    let org_sexp = out.stderr;
+    Ok(String::from_utf8(org_sexp)?)
+}
+
+pub fn emacs_parse_file_org_document<P>(file_path: P) -> Result<String, Box<dyn std::error::Error>>
+where
+    P: AsRef<Path>,
+{
+    let file_path = file_path.as_ref().canonicalize()?;
+    let containing_directory = file_path.parent().ok_or(format!(
+        "Failed to get containing directory for path {}",
+        file_path.display()
+    ))?;
+    let elisp_script = format!(
+        r#"(progn
+     (require 'org)
+     (defun org-table-align () t)
+     (org-mode)
+     (message "%s" (pp-to-string (org-element-parse-buffer)))
+)"#
+    );
+    let mut cmd = Command::new("emacs");
+    let cmd = cmd
+        .current_dir(containing_directory)
+        .arg("-q")
+        .arg("--no-site-file")
+        .arg("--no-splash")
+        .arg("--batch")
+        .arg("--insert")
+        .arg(file_path.as_os_str())
+        .arg("--eval")
+        .arg(elisp_script);
+    let out = cmd.output()?;
     out.status.exit_ok()?;
     let org_sexp = out.stderr;
     Ok(String::from_utf8(org_sexp)?)
@@ -55,7 +94,7 @@ pub fn get_emacs_version() -> Result<String, Box<dyn std::error::Error>> {
      (message "%s" (version))
 )"#;
     let mut cmd = Command::new("emacs");
-    let proc = cmd
+    let cmd = cmd
         .arg("-q")
         .arg("--no-site-file")
         .arg("--no-splash")
@@ -63,7 +102,7 @@ pub fn get_emacs_version() -> Result<String, Box<dyn std::error::Error>> {
         .arg("--eval")
         .arg(elisp_script);
 
-    let out = proc.output()?;
+    let out = cmd.output()?;
     out.status.exit_ok()?;
     Ok(String::from_utf8(out.stderr)?)
 }
@@ -74,7 +113,7 @@ pub fn get_org_mode_version() -> Result<String, Box<dyn std::error::Error>> {
      (message "%s" (org-version nil t nil))
 )"#;
     let mut cmd = Command::new("emacs");
-    let proc = cmd
+    let cmd = cmd
         .arg("-q")
         .arg("--no-site-file")
         .arg("--no-splash")
@@ -82,7 +121,7 @@ pub fn get_org_mode_version() -> Result<String, Box<dyn std::error::Error>> {
         .arg("--eval")
         .arg(elisp_script);
 
-    let out = proc.output()?;
+    let out = cmd.output()?;
     out.status.exit_ok()?;
     Ok(String::from_utf8(out.stderr)?)
 }

src/compare/sexp.rs

@@ -16,9 +16,6 @@ use nom::sequence::delimited;
 use nom::sequence::preceded;
 use nom::sequence::tuple;
 
-use super::org_source::convert_error;
-use super::org_source::OrgSource;
-use super::util::get_consumed;
 use crate::error::Res;
 
 #[derive(Debug)]
@@ -31,8 +28,8 @@ pub enum Token<'s> {
 
 #[derive(Debug)]
 pub struct TextWithProperties<'s> {
-    pub text: &'s str,
-    pub properties: Vec<Token<'s>>,
+    pub(crate) text: &'s str,
+    pub(crate) properties: Vec<Token<'s>>,
 }
 
 enum ParseState {
@@ -41,35 +38,39 @@ enum ParseState {
 }
 
 impl<'s> Token<'s> {
-    pub fn as_vector<'p>(&'p self) -> Result<&'p Vec<Token<'s>>, Box<dyn std::error::Error>> {
+    pub(crate) fn as_vector<'p>(
+        &'p self,
+    ) -> Result<&'p Vec<Token<'s>>, Box<dyn std::error::Error>> {
         Ok(match self {
             Token::Vector(children) => Ok(children),
             _ => Err(format!("wrong token type, expected vector: {:?}", self)),
         }?)
     }
 
-    pub fn as_list<'p>(&'p self) -> Result<&'p Vec<Token<'s>>, Box<dyn std::error::Error>> {
+    pub(crate) fn as_list<'p>(&'p self) -> Result<&'p Vec<Token<'s>>, Box<dyn std::error::Error>> {
         Ok(match self {
             Token::List(children) => Ok(children),
             _ => Err(format!("wrong token type, expected list: {:?}", self)),
         }?)
     }
 
-    pub fn as_atom<'p>(&'p self) -> Result<&'s str, Box<dyn std::error::Error>> {
+    pub(crate) fn as_atom<'p>(&'p self) -> Result<&'s str, Box<dyn std::error::Error>> {
         Ok(match self {
             Token::Atom(body) => Ok(*body),
             _ => Err(format!("wrong token type, expected atom: {:?}", self)),
         }?)
     }
 
-    pub fn as_text<'p>(&'p self) -> Result<&'p TextWithProperties<'s>, Box<dyn std::error::Error>> {
+    pub(crate) fn as_text<'p>(
+        &'p self,
+    ) -> Result<&'p TextWithProperties<'s>, Box<dyn std::error::Error>> {
         Ok(match self {
             Token::TextWithProperties(body) => Ok(body),
             _ => Err(format!("wrong token type, expected text: {:?}", self)),
         }?)
     }
 
-    pub fn as_map<'p>(
+    pub(crate) fn as_map<'p>(
         &'p self,
     ) -> Result<HashMap<&'s str, &'p Token<'s>>, Box<dyn std::error::Error>> {
         let mut hashmap = HashMap::new();
@@ -95,7 +96,26 @@ impl<'s> Token<'s> {
     }
 }
 
-pub fn unquote(text: &str) -> Result<String, Box<dyn std::error::Error>> {
+/// Check if the child string slice is a slice of the parent string slice.
+fn is_slice_of(parent: &str, child: &str) -> bool {
+    let parent_start = parent.as_ptr() as usize;
+    let parent_end = parent_start + parent.len();
+    let child_start = child.as_ptr() as usize;
+    let child_end = child_start + child.len();
+    child_start >= parent_start && child_end <= parent_end
+}
+
+/// Get a slice of the string that was consumed in a parser using the original input to the parser and the remaining input after the parser.
+pub fn get_consumed<'s>(input: &'s str, remaining: &'s str) -> &'s str {
+    assert!(is_slice_of(input, remaining));
+    let source = {
+        let offset = remaining.as_ptr() as usize - input.as_ptr() as usize;
+        &input[..offset]
+    };
+    source.into()
+}
+
+pub(crate) fn unquote(text: &str) -> Result<String, Box<dyn std::error::Error>> {
     let mut out = String::with_capacity(text.len());
     if !text.starts_with(r#"""#) {
         return Err("Quoted text does not start with quote.".into());
@@ -132,29 +152,20 @@ pub fn unquote(text: &str) -> Result<String, Box<dyn std::error::Error>> {
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-pub fn sexp_with_padding<'s>(input: &'s str) -> Res<&'s str, Token<'s>> {
+pub fn sexp<'s>(input: &'s str) -> Res<&'s str, Token<'s>> {
     let (remaining, _) = multispace0(input)?;
-    let remaining = OrgSource::new(remaining);
-    let (remaining, tkn) = token(remaining)
-        .map(|(rem, out)| (Into::<&str>::into(rem), out))
-        .map_err(convert_error)?;
+    let (remaining, tkn) = token(remaining).map(|(rem, out)| (Into::<&str>::into(rem), out))?;
     let (remaining, _) = multispace0(remaining)?;
     Ok((remaining, tkn))
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-pub fn sexp<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Token<'s>> {
-    let (remaining, tkn) = token(input)?;
-    Ok((remaining, tkn))
-}
-
-#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn token<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Token<'s>> {
+fn token<'s>(input: &'s str) -> Res<&'s str, Token<'s>> {
     alt((list, vector, atom))(input)
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn list<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Token<'s>> {
+fn list<'s>(input: &'s str) -> Res<&'s str, Token<'s>> {
     let (remaining, _) = tag("(")(input)?;
     let (remaining, children) = delimited(
         multispace0,
@@ -166,7 +177,7 @@ fn list<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Token<'s>> {
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn vector<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Token<'s>> {
+fn vector<'s>(input: &'s str) -> Res<&'s str, Token<'s>> {
     let (remaining, _) = tag("[")(input)?;
     let (remaining, children) = delimited(
         multispace0,
@@ -178,7 +189,7 @@ fn vector<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Token<'s>> {
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn atom<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Token<'s>> {
+fn atom<'s>(input: &'s str) -> Res<&'s str, Token<'s>> {
     not(peek(one_of(")]")))(input)?;
     alt((
         text_with_properties,
@@ -189,7 +200,7 @@ fn atom<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Token<'s>> {
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn unquoted_atom<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Token<'s>> {
+fn unquoted_atom<'s>(input: &'s str) -> Res<&'s str, Token<'s>> {
     let (remaining, body) = take_till1(|c| match c {
         ' ' | '\t' | '\r' | '\n' | ')' | ']' => true,
         _ => false,
@@ -198,7 +209,7 @@ fn unquoted_atom<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Token<'s>> {
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn quoted_atom<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Token<'s>> {
+fn quoted_atom<'s>(input: &'s str) -> Res<&'s str, Token<'s>> {
     let (remaining, _) = tag(r#"""#)(input)?;
     let (remaining, _) = escaped(
         take_till1(|c| match c {
@@ -214,7 +225,7 @@ fn quoted_atom<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Token<'s>> {
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn hash_notation<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Token<'s>> {
+fn hash_notation<'s>(input: &'s str) -> Res<&'s str, Token<'s>> {
     let (remaining, _) = tag("#<")(input)?;
     let (remaining, _body) = take_till1(|c| match c {
         '>' => true,
@@ -225,7 +236,7 @@ fn hash_notation<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Token<'s>> {
     Ok((remaining, Token::Atom(source.into())))
 }
 
-fn text_with_properties<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Token<'s>> {
+fn text_with_properties<'s>(input: &'s str) -> Res<&'s str, Token<'s>> {
     let (remaining, _) = tag("#(")(input)?;
     let (remaining, (text, props)) = delimited(
         multispace0,
@@ -255,7 +266,7 @@ mod tests {
     #[test]
     fn simple() {
         let input = "  (foo bar baz )  ";
-        let (remaining, parsed) = sexp_with_padding(input).expect("Parse the input");
+        let (remaining, parsed) = sexp(input).expect("Parse the input");
         assert_eq!(remaining, "");
         assert!(match parsed {
             Token::Atom(_) => false,
@@ -268,7 +279,7 @@ mod tests {
     #[test]
     fn quoted() {
         let input = r#"  ("foo" bar baz )  "#;
-        let (remaining, parsed) = sexp_with_padding(input).expect("Parse the input");
+        let (remaining, parsed) = sexp(input).expect("Parse the input");
         assert_eq!(remaining, "");
         assert!(match parsed {
             Token::Atom(_) => false,
@@ -292,7 +303,7 @@ mod tests {
     #[test]
     fn quoted_containing_paren() {
         let input = r#"  (foo "b(a)r" baz )  "#;
-        let (remaining, parsed) = sexp_with_padding(input).expect("Parse the input");
+        let (remaining, parsed) = sexp(input).expect("Parse the input");
         assert_eq!(remaining, "");
         assert!(match parsed {
             Token::List(_) => true,
@@ -328,7 +339,7 @@ mod tests {
     #[test]
     fn string_containing_escaped_characters() {
         let input = r#"  (foo "\\( x=2 \\)" bar)  "#;
-        let (remaining, parsed) = sexp_with_padding(input).expect("Parse the input");
+        let (remaining, parsed) = sexp(input).expect("Parse the input");
         assert_eq!(remaining, "");
         assert!(match parsed {
             Token::Atom(_) => false,

src/compare/util.rs

@@ -1,5 +1,5 @@
-use crate::parser::sexp::Token;
-use crate::parser::Source;
+use super::sexp::Token;
+use crate::types::Source;
 
 /// Check if the child string slice is a slice of the parent string slice.
 fn is_slice_of(parent: &str, child: &str) -> bool {
@@ -13,7 +13,7 @@ fn is_slice_of(parent: &str, child: &str) -> bool {
 /// Get the offset into source that the rust object exists at.
 ///
 /// These offsets are zero-based unlike the elisp ones.
-pub fn get_offsets<'s, S: Source<'s>>(source: &'s str, rust_object: &'s S) -> (usize, usize) {
+fn get_offsets<'s, S: Source<'s>>(source: &'s str, rust_object: &'s S) -> (usize, usize) {
     let rust_object_source = rust_object.get_source();
     assert!(is_slice_of(source, rust_object_source));
     let offset = rust_object_source.as_ptr() as usize - source.as_ptr() as usize;
@@ -21,7 +21,10 @@ pub fn get_offsets<'s, S: Source<'s>>(source: &'s str, rust_object: &'s S) -> (u
     (offset, end)
 }
 
-pub fn assert_name<'s>(emacs: &'s Token<'s>, name: &str) -> Result<(), Box<dyn std::error::Error>> {
+pub(crate) fn assert_name<'s>(
+    emacs: &'s Token<'s>,
+    name: &str,
+) -> Result<(), Box<dyn std::error::Error>> {
     let children = emacs.as_list()?;
     let first_child = children
         .first()
@@ -37,7 +40,7 @@ pub fn assert_name<'s>(emacs: &'s Token<'s>, name: &str) -> Result<(), Box<dyn s
     Ok(())
 }
 
-pub fn assert_bounds<'s, S: Source<'s>>(
+pub(crate) fn assert_bounds<'s, S: Source<'s>>(
     source: &'s str,
     emacs: &'s Token<'s>,
     rust: &'s S,
@@ -50,8 +53,11 @@ pub fn assert_bounds<'s, S: Source<'s>>(
         standard_properties.end.ok_or("Token should have an end.")?,
     );
     let (rust_begin, rust_end) = get_offsets(source, rust);
-    if (rust_begin + 1) != begin || (rust_end + 1) != end {
-        Err(format!("Rust bounds (in bytes) ({rust_begin}, {rust_end}) do not match emacs bounds ({emacs_begin}, {emacs_end})", rust_begin = rust_begin + 1, rust_end = rust_end + 1, emacs_begin=begin, emacs_end=end))?;
+    let rust_begin_char_offset = (&source[..rust_begin]).chars().count();
+    let rust_end_char_offset =
+        rust_begin_char_offset + (&source[rust_begin..rust_end]).chars().count();
+    if (rust_begin_char_offset + 1) != begin || (rust_end_char_offset + 1) != end {
+        Err(format!("Rust bounds (in chars) ({rust_begin}, {rust_end}) do not match emacs bounds ({emacs_begin}, {emacs_end})", rust_begin = rust_begin_char_offset + 1, rust_end = rust_end_char_offset + 1, emacs_begin=begin, emacs_end=end))?;
     }
 
     Ok(())
@@ -138,7 +144,12 @@ fn maybe_token_to_usize(
         .map_or(Ok(None), |r| r.map(Some))?)
 }
 
-pub fn get_property<'s, 'x>(
+/// Get a named property from the emacs token.
+///
+/// Returns Ok(None) if value is nil.
+///
+/// Returns error if the attribute is not specified on the token at all.
+pub(crate) fn get_property<'s, 'x>(
     emacs: &'s Token<'s>,
     key: &'x str,
 ) -> Result<Option<&'s Token<'s>>, Box<dyn std::error::Error>> {

src/context/context.rs

@@ -0,0 +1,185 @@
+use std::marker::PhantomData;
+
+use nom::combinator::eof;
+use nom::IResult;
+
+use super::exiting::ExitClass;
+use super::global_settings::GlobalSettings;
+use super::list::List;
+use super::DynContextMatcher;
+use super::RefContext;
+use crate::error::CustomError;
+use crate::error::MyError;
+use crate::error::Res;
+use crate::parser::OrgSource;
+
+#[derive(Debug)]
+pub(crate) enum ContextElement<'r, 's> {
+    /// Stores a parser that indicates that children should exit upon matching an exit matcher.
+    ExitMatcherNode(ExitMatcherNode<'r>),
+
+    /// Stores the name of the current element to prevent directly nesting elements of the same type.
+    Context(&'r str),
+
+    /// Stores the name of the current object to prevent directly nesting elements of the same type.
+    ContextObject(&'r str),
+
+    /// Indicates if elements should consume the whitespace after them.
+    ConsumeTrailingWhitespace(bool),
+
+    /// This is just here to use the 's lifetime until I'm sure we can eliminate it from ContextElement.
+    #[allow(dead_code)]
+    Placeholder(PhantomData<&'s str>),
+}
+
+pub(crate) struct ExitMatcherNode<'r> {
+    // TODO: Should this be "&'r DynContextMatcher<'c>" ?
+    pub(crate) exit_matcher: &'r DynContextMatcher<'r>,
+    pub(crate) class: ExitClass,
+}
+
+impl<'r> std::fmt::Debug for ExitMatcherNode<'r> {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        let mut formatter = f.debug_struct("ExitMatcherNode");
+        formatter.field("class", &self.class.to_string());
+        formatter.finish()
+    }
+}
+
+#[derive(Debug)]
+pub(crate) struct Context<'g, 'r, 's> {
+    global_settings: &'g GlobalSettings<'g, 's>,
+    tree: List<'r, &'r ContextElement<'r, 's>>,
+}
+
+impl<'g, 'r, 's> Context<'g, 'r, 's> {
+    pub(crate) fn new(
+        global_settings: &'g GlobalSettings<'g, 's>,
+        tree: List<'r, &'r ContextElement<'r, 's>>,
+    ) -> Self {
+        Self {
+            global_settings,
+            tree,
+        }
+    }
+
+    pub(crate) fn with_additional_node(&'r self, new_element: &'r ContextElement<'r, 's>) -> Self {
+        let new_tree = self.tree.push(new_element);
+        Self::new(self.global_settings, new_tree)
+    }
+
+    pub(crate) fn iter(&'r self) -> super::list::Iter<'r, &'r ContextElement<'r, 's>> {
+        self.tree.iter()
+    }
+
+    fn iter_context(&'r self) -> Iter<'g, 'r, 's> {
+        Iter {
+            next: self.tree.iter_list(),
+            global_settings: self.global_settings,
+        }
+    }
+
+    pub(crate) fn get_parent(&'r self) -> Option<Self> {
+        self.tree.get_parent().map(|parent_tree| Self {
+            global_settings: self.global_settings,
+            tree: parent_tree.clone(),
+        })
+    }
+
+    fn get_data(&self) -> &ContextElement<'r, 's> {
+        self.tree.get_data()
+    }
+
+    pub(crate) fn get_global_settings(&self) -> &'g GlobalSettings<'g, 's> {
+        self.global_settings
+    }
+
+    pub(crate) fn with_global_settings<'gg>(
+        &self,
+        new_settings: &'gg GlobalSettings<'gg, 's>,
+    ) -> Context<'gg, 'r, 's> {
+        Context {
+            global_settings: new_settings,
+            tree: self.tree.clone(),
+        }
+    }
+
+    #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
+    pub(crate) fn check_exit_matcher(
+        &'r self,
+        i: OrgSource<'s>,
+    ) -> IResult<OrgSource<'s>, OrgSource<'s>, CustomError<OrgSource<'s>>> {
+        let mut current_class_filter = ExitClass::Gamma;
+        for current_node in self.iter_context() {
+            let context_element = current_node.get_data();
+            match context_element {
+                ContextElement::ExitMatcherNode(exit_matcher) => {
+                    if exit_matcher.class as u32 <= current_class_filter as u32 {
+                        current_class_filter = exit_matcher.class;
+                        let local_result = (exit_matcher.exit_matcher)(&current_node, i);
+                        if local_result.is_ok() {
+                            return local_result;
+                        }
+                    }
+                }
+                _ => {}
+            };
+        }
+        // TODO: Make this a specific error instead of just a generic MyError
+        return Err(nom::Err::Error(CustomError::MyError(MyError(
+            "NoExit".into(),
+        ))));
+    }
+
+    /// Indicates if elements should consume the whitespace after them.
+    ///
+    /// Defaults to true.
+    pub(crate) fn should_consume_trailing_whitespace(&self) -> bool {
+        self._should_consume_trailing_whitespace().unwrap_or(true)
+    }
+
+    fn _should_consume_trailing_whitespace(&self) -> Option<bool> {
+        for current_node in self.iter() {
+            match current_node {
+                ContextElement::ConsumeTrailingWhitespace(should) => {
+                    return Some(*should);
+                }
+                _ => {}
+            }
+        }
+        None
+    }
+}
+
+#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
+fn document_end<'b, 'g, 'r, 's>(
+    _context: RefContext<'b, 'g, 'r, 's>,
+    input: OrgSource<'s>,
+) -> Res<OrgSource<'s>, OrgSource<'s>> {
+    eof(input)
+}
+
+struct Iter<'g, 'r, 's> {
+    global_settings: &'g GlobalSettings<'g, 's>,
+    next: super::list::IterList<'r, &'r ContextElement<'r, 's>>,
+}
+
+impl<'g, 'r, 's> Iterator for Iter<'g, 'r, 's> {
+    type Item = Context<'g, 'r, 's>;
+
+    fn next(&mut self) -> Option<Self::Item> {
+        let next_tree = self.next.next();
+        let ret =
+            next_tree.map(|parent_tree| Context::new(self.global_settings, parent_tree.clone()));
+        ret
+    }
+}
+
+impl<'r, 's> ContextElement<'r, 's> {
+    pub(crate) fn document_context() -> Self {
+        Self::ExitMatcherNode(ExitMatcherNode {
+            exit_matcher: &document_end,
+            class: ExitClass::Document,
+        })
+    }
+}

src/context/exiting.rs

@@ -0,0 +1,13 @@
+#[derive(Debug, Copy, Clone)]
+pub(crate) enum ExitClass {
+    Document = 1,
+    Alpha = 2,
+    Beta = 3,
+    Gamma = 4,
+}
+
+impl std::fmt::Display for ExitClass {
+    fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
+        write!(f, "{:?}", self)
+    }
+}

src/context/file_access_interface.rs

@@ -0,0 +1,23 @@
+use std::fmt::Debug;
+use std::path::PathBuf;
+
+pub trait FileAccessInterface: Debug {
+    fn read_file(&self, path: &str) -> Result<String, std::io::Error>;
+}
+
+#[derive(Debug, Clone)]
+pub struct LocalFileAccessInterface {
+    pub working_directory: Option<PathBuf>,
+}
+
+impl FileAccessInterface for LocalFileAccessInterface {
+    fn read_file(&self, path: &str) -> Result<String, std::io::Error> {
+        let final_path = self
+            .working_directory
+            .as_ref()
+            .map(PathBuf::as_path)
+            .map(|pb| pb.join(path))
+            .unwrap_or_else(|| PathBuf::from(path));
+        Ok(std::fs::read_to_string(final_path)?)
+    }
+}

src/context/global_settings.rs

@@ -0,0 +1,58 @@
+use std::collections::BTreeSet;
+
+use super::FileAccessInterface;
+use super::LocalFileAccessInterface;
+use crate::types::IndentationLevel;
+use crate::types::Object;
+
+// TODO: Ultimately, I think we'll need most of this: https://orgmode.org/manual/In_002dbuffer-Settings.html
+
+#[derive(Debug, Clone)]
+pub struct GlobalSettings<'g, 's> {
+    pub radio_targets: Vec<&'g Vec<Object<'s>>>,
+    pub file_access: &'g dyn FileAccessInterface,
+    pub in_progress_todo_keywords: BTreeSet<String>,
+    pub complete_todo_keywords: BTreeSet<String>,
+    /// Set to true to allow for plain lists using single letters as the bullet in the same way that numbers are used.
+    ///
+    /// Corresponds to the org-list-allow-alphabetical elisp variable.
+    pub org_list_allow_alphabetical: bool,
+
+    /// How many spaces a tab should be equal to.
+    ///
+    /// Corresponds to the tab-width elisp variable.
+    pub tab_width: IndentationLevel,
+
+    /// Whether to only allow odd headline levels.
+    ///
+    /// Corresponds to org-odd-levels-only elisp variable.
+    pub odd_levels_only: HeadlineLevelFilter,
+}
+
+impl<'g, 's> GlobalSettings<'g, 's> {
+    fn new() -> GlobalSettings<'g, 's> {
+        GlobalSettings {
+            radio_targets: Vec::new(),
+            file_access: &LocalFileAccessInterface {
+                working_directory: None,
+            },
+            in_progress_todo_keywords: BTreeSet::new(),
+            complete_todo_keywords: BTreeSet::new(),
+            org_list_allow_alphabetical: false,
+            tab_width: 8,
+            odd_levels_only: HeadlineLevelFilter::OddEven,
+        }
+    }
+}
+
+impl<'g, 's> Default for GlobalSettings<'g, 's> {
+    fn default() -> GlobalSettings<'g, 's> {
+        GlobalSettings::new()
+    }
+}
+
+#[derive(Debug, Clone)]
+pub enum HeadlineLevelFilter {
+    Odd,
+    OddEven,
+}

src/context/list.rs

@@ -0,0 +1,69 @@
+use std::fmt::Debug;
+
+#[derive(Debug, Clone)]
+pub(crate) struct List<'parent, T> {
+    data: T,
+    parent: Link<'parent, T>,
+}
+
+type Link<'parent, T> = Option<&'parent List<'parent, T>>;
+
+impl<'parent, T> List<'parent, T> {
+    pub(crate) fn new(first_item: T) -> Self {
+        Self {
+            data: first_item,
+            parent: None,
+        }
+    }
+
+    pub(crate) fn get_data(&self) -> &T {
+        &self.data
+    }
+
+    pub(crate) fn get_parent(&'parent self) -> Link<'parent, T> {
+        self.parent
+    }
+
+    pub(crate) fn iter(&self) -> Iter<'_, T> {
+        Iter { next: Some(self) }
+    }
+
+    pub(crate) fn iter_list(&self) -> IterList<'_, T> {
+        IterList { next: Some(self) }
+    }
+
+    pub(crate) fn push(&'parent self, item: T) -> Self {
+        Self {
+            data: item,
+            parent: Some(self),
+        }
+    }
+}
+
+pub(crate) struct Iter<'a, T> {
+    next: Link<'a, T>,
+}
+
+impl<'a, T> Iterator for Iter<'a, T> {
+    type Item = &'a T;
+
+    fn next(&mut self) -> Option<Self::Item> {
+        let ret = self.next.map(|link| link.get_data());
+        self.next = self.next.map(|link| link.get_parent()).flatten();
+        ret
+    }
+}
+
+pub(crate) struct IterList<'a, T> {
+    next: Link<'a, T>,
+}
+
+impl<'a, T> Iterator for IterList<'a, T> {
+    type Item = &'a List<'a, T>;
+
+    fn next(&mut self) -> Option<Self::Item> {
+        let ret = self.next;
+        self.next = self.next.map(|this| this.get_parent()).flatten();
+        ret
+    }
+}

src/context/mod.rs

@@ -0,0 +1,30 @@
+use crate::error::Res;
+use crate::parser::OrgSource;
+
+mod context;
+mod exiting;
+mod file_access_interface;
+mod global_settings;
+mod list;
+mod parser_with_context;
+
+pub(crate) type RefContext<'b, 'g, 'r, 's> = &'b Context<'g, 'r, 's>;
+pub(crate) trait ContextMatcher = for<'b, 'g, 'r, 's> Fn(
+    RefContext<'b, 'g, 'r, 's>,
+    OrgSource<'s>,
+) -> Res<OrgSource<'s>, OrgSource<'s>>;
+type DynContextMatcher<'c> = dyn ContextMatcher + 'c;
+pub(crate) trait Matcher = for<'s> Fn(OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>>;
+#[allow(dead_code)]
+type DynMatcher<'c> = dyn Matcher + 'c;
+
+pub(crate) use context::Context;
+pub(crate) use context::ContextElement;
+pub(crate) use context::ExitMatcherNode;
+pub(crate) use exiting::ExitClass;
+pub use file_access_interface::FileAccessInterface;
+pub use file_access_interface::LocalFileAccessInterface;
+pub use global_settings::GlobalSettings;
+pub use global_settings::HeadlineLevelFilter;
+pub(crate) use list::List;
+pub(crate) use parser_with_context::parser_with_context;

src/error/error.rs

@@ -2,17 +2,18 @@ use nom::error::ErrorKind;
 use nom::error::ParseError;
 use nom::IResult;
 
-pub type Res<T, U> = IResult<T, U, CustomError<T>>;
+pub(crate) type Res<T, U> = IResult<T, U, CustomError<T>>;
 
 // TODO: MyError probably shouldn't be based on the same type as the input type since it's used exclusively with static strings right now.
-#[derive(Debug, PartialEq)]
+#[derive(Debug)]
 pub enum CustomError<I> {
     MyError(MyError<I>),
     Nom(I, ErrorKind),
+    IO(std::io::Error),
 }
 
-#[derive(Debug, PartialEq)]
-pub struct MyError<I>(pub I);
+#[derive(Debug)]
+pub struct MyError<I>(pub(crate) I);
 
 impl<I> ParseError<I> for CustomError<I> {
     fn from_error_kind(input: I, kind: ErrorKind) -> Self {
@@ -24,3 +25,9 @@ impl<I> ParseError<I> for CustomError<I> {
         other
     }
 }
+
+impl<I> From<std::io::Error> for CustomError<I> {
+    fn from(value: std::io::Error) -> Self {
+        CustomError::IO(value)
+    }
+}

src/error/mod.rs

@@ -1,4 +1,4 @@
 mod error;
-pub use error::CustomError;
-pub use error::MyError;
-pub use error::Res;
+pub(crate) use error::CustomError;
+pub(crate) use error::MyError;
+pub(crate) use error::Res;

src/init_tracing.rs

@@ -10,7 +10,7 @@ const SERVICE_NAME: &'static str = "organic";
 // Despite the obvious verbosity that fully-qualifying everything causes, in these functions I am fully-qualifying everything relating to tracing. This is because the tracing feature involves multiple libraries working together and so I think it is beneficial to see which libraries contribute which bits.
 
 #[cfg(feature = "tracing")]
-pub fn init_telemetry() -> Result<(), Box<dyn std::error::Error>> {
+pub(crate) fn init_telemetry() -> Result<(), Box<dyn std::error::Error>> {
     // by default it will hit http://localhost:4317 with a gRPC payload
     // TODO: I think the endpoint can be controlled by the OTEL_EXPORTER_OTLP_TRACES_ENDPOINT env variable instead of hard-coded into this code base. Regardless, I am the only developer right now so I am not too concerned.
     let exporter = opentelemetry_otlp::new_exporter()
@@ -55,17 +55,17 @@ pub fn init_telemetry() -> Result<(), Box<dyn std::error::Error>> {
 }
 
 #[cfg(feature = "tracing")]
-pub fn shutdown_telemetry() -> Result<(), Box<dyn std::error::Error>> {
+pub(crate) fn shutdown_telemetry() -> Result<(), Box<dyn std::error::Error>> {
     opentelemetry::global::shutdown_tracer_provider();
     Ok(())
 }
 
 #[cfg(not(feature = "tracing"))]
-pub fn init_telemetry() -> Result<(), Box<dyn std::error::Error>> {
+pub(crate) fn init_telemetry() -> Result<(), Box<dyn std::error::Error>> {
     Ok(())
 }
 
 #[cfg(not(feature = "tracing"))]
-pub fn shutdown_telemetry() -> Result<(), Box<dyn std::error::Error>> {
+pub(crate) fn shutdown_telemetry() -> Result<(), Box<dyn std::error::Error>> {
     Ok(())
 }

src/lib.rs

@@ -1,16 +1,16 @@
 #![feature(round_char_boundary)]
 #![feature(exit_status_error)]
+#![feature(trait_alias)]
+// TODO: #![warn(missing_docs)]
 
 #[cfg(feature = "compare")]
-mod compare;
-#[cfg(feature = "compare")]
-pub use compare::compare_document;
-#[cfg(feature = "compare")]
-pub use compare::emacs_parse_org_document;
-#[cfg(feature = "compare")]
-pub use compare::get_emacs_version;
-#[cfg(feature = "compare")]
-pub use compare::get_org_mode_version;
+pub mod compare;
 
+mod context;
 mod error;
 pub mod parser;
+pub mod types;
+
+pub use context::FileAccessInterface;
+pub use context::GlobalSettings;
+pub use context::LocalFileAccessInterface;

src/main.rs

@@ -1,17 +1,12 @@
 #![feature(round_char_boundary)]
+#![feature(exact_size_is_empty)]
 use std::io::Read;
+use std::path::Path;
 
-use ::organic::parser::document;
-#[cfg(feature = "compare")]
-use organic::compare_document;
-#[cfg(feature = "compare")]
-use organic::emacs_parse_org_document;
-#[cfg(feature = "compare")]
-use organic::get_emacs_version;
-#[cfg(feature = "compare")]
-use organic::get_org_mode_version;
-#[cfg(feature = "compare")]
-use organic::parser::sexp::sexp_with_padding;
+use ::organic::parser::parse;
+use organic::parser::parse_with_settings;
+use organic::GlobalSettings;
+use organic::LocalFileAccessInterface;
 
 #[cfg(feature = "tracing")]
 use crate::init_tracing::init_telemetry;
@@ -39,8 +34,16 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
 fn main_body() -> Result<(), Box<dyn std::error::Error>> {
-    let org_contents = read_stdin_to_string()?;
-    run_compare(org_contents)
+    let args = std::env::args().skip(1);
+    if args.is_empty() {
+        let org_contents = read_stdin_to_string()?;
+        run_anonymous_parse(org_contents)
+    } else {
+        for arg in args {
+            run_parse_on_file(arg)?
+        }
+        Ok(())
+    }
 }
 
 fn read_stdin_to_string() -> Result<String, Box<dyn std::error::Error>> {
@@ -51,42 +54,28 @@ fn read_stdin_to_string() -> Result<String, Box<dyn std::error::Error>> {
     Ok(stdin_contents)
 }
 
-#[cfg(feature = "compare")]
-fn run_compare<P: AsRef<str>>(org_contents: P) -> Result<(), Box<dyn std::error::Error>> {
-    let emacs_version = get_emacs_version()?;
-    let org_mode_version = get_org_mode_version()?;
-    let org_contents = org_contents.as_ref();
-    eprintln!("Using emacs version: {}", emacs_version.trim());
-    eprintln!("Using org-mode version: {}", org_mode_version.trim());
-    let (remaining, rust_parsed) = document(org_contents).map_err(|e| e.to_string())?;
-    let org_sexp = emacs_parse_org_document(org_contents)?;
-    let (_remaining, parsed_sexp) =
-        sexp_with_padding(org_sexp.as_str()).map_err(|e| e.to_string())?;
-
-    println!("{}\n\n\n", org_contents);
-    println!("{}", org_sexp);
-    println!("{:#?}", rust_parsed);
-
-    // We do the diffing after printing out both parsed forms in case the diffing panics
-    let diff_result = compare_document(&parsed_sexp, &rust_parsed)?;
-    diff_result.print(org_contents)?;
-
-    if diff_result.is_bad() {
-        Err("Diff results do not match.")?;
-    }
-    if remaining != "" {
-        Err(format!("There was unparsed text remaining: {}", remaining))?;
-    }
-
-    Ok(())
-}
-
-#[cfg(not(feature = "compare"))]
-fn run_compare<P: AsRef<str>>(org_contents: P) -> Result<(), Box<dyn std::error::Error>> {
-    eprintln!(
-        "This program was built with compare disabled. Only parsing with organic, not comparing."
-    );
-    let (_remaining, rust_parsed) = document(org_contents.as_ref()).map_err(|e| e.to_string())?;
+fn run_anonymous_parse<P: AsRef<str>>(org_contents: P) -> Result<(), Box<dyn std::error::Error>> {
+    let rust_parsed = parse(org_contents.as_ref())?;
+    println!("{:#?}", rust_parsed);
+    Ok(())
+}
+
+fn run_parse_on_file<P: AsRef<Path>>(org_path: P) -> Result<(), Box<dyn std::error::Error>> {
+    let org_path = org_path.as_ref();
+    let parent_directory = org_path
+        .parent()
+        .ok_or("Should be contained inside a directory.")?;
+    let org_contents = std::fs::read_to_string(org_path)?;
+    let org_contents = org_contents.as_str();
+    let file_access_interface = LocalFileAccessInterface {
+        working_directory: Some(parent_directory.to_path_buf()),
+    };
+    let global_settings = {
+        let mut global_settings = GlobalSettings::default();
+        global_settings.file_access = &file_access_interface;
+        global_settings
+    };
+    let rust_parsed = parse_with_settings(org_contents, &global_settings)?;
     println!("{:#?}", rust_parsed);
     Ok(())
 }

src/parser/angle_link.rs

@@ -5,20 +5,21 @@ use nom::combinator::recognize;
 use nom::multi::many_till;
 
 use super::org_source::OrgSource;
-use super::Context;
+use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
+use crate::context::parser_with_context;
+use crate::context::ContextElement;
+use crate::context::ExitClass;
+use crate::context::ExitMatcherNode;
+use crate::context::RefContext;
 use crate::error::Res;
-use crate::parser::exiting::ExitClass;
-use crate::parser::parser_context::ContextElement;
-use crate::parser::parser_context::ExitMatcherNode;
-use crate::parser::parser_with_context::parser_with_context;
 use crate::parser::plain_link::protocol;
 use crate::parser::util::exit_matcher_parser;
 use crate::parser::util::get_consumed;
-use crate::parser::AngleLink;
+use crate::types::AngleLink;
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-pub fn angle_link<'r, 's>(
-    context: Context<'r, 's>,
+pub(crate) fn angle_link<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, AngleLink<'s>> {
     let (remaining, _) = tag("<")(input)?;
@@ -26,6 +27,8 @@ pub fn angle_link<'r, 's>(
     let (remaining, _separator) = tag(":")(remaining)?;
     let (remaining, path) = path_angle(context, remaining)?;
     let (remaining, _) = tag(">")(remaining)?;
+    let (remaining, _trailing_whitespace) =
+        maybe_consume_object_trailing_whitespace_if_not_exiting(context, remaining)?;
     let source = get_consumed(input, remaining);
     Ok((
         remaining,
@@ -38,15 +41,15 @@ pub fn angle_link<'r, 's>(
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn path_angle<'r, 's>(
-    context: Context<'r, 's>,
+fn path_angle<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, OrgSource<'s>> {
-    let parser_context =
-        context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
-            class: ExitClass::Gamma,
-            exit_matcher: &path_angle_end,
-        }));
+    let parser_context = ContextElement::ExitMatcherNode(ExitMatcherNode {
+        class: ExitClass::Gamma,
+        exit_matcher: &path_angle_end,
+    });
+    let parser_context = context.with_additional_node(&parser_context);
 
     let exit_matcher = parser_with_context!(exit_matcher_parser)(&parser_context);
 
@@ -55,8 +58,8 @@ fn path_angle<'r, 's>(
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn path_angle_end<'r, 's>(
-    _context: Context<'r, 's>,
+fn path_angle_end<'b, 'g, 'r, 's>(
+    _context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, OrgSource<'s>> {
     tag(">")(input)

src/parser/citation.rs

@@ -2,7 +2,6 @@ use nom::branch::alt;
 use nom::bytes::complete::tag;
 use nom::bytes::complete::tag_no_case;
 use nom::character::complete::anychar;
-use nom::character::complete::space0;
 use nom::combinator::opt;
 use nom::combinator::recognize;
 use nom::combinator::verify;
@@ -14,24 +13,26 @@ use nom::sequence::tuple;
 use super::citation_reference::must_balance_bracket;
 use super::org_source::BracketDepth;
 use super::org_source::OrgSource;
-use super::Context;
+use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
+use crate::context::parser_with_context;
+use crate::context::ContextElement;
+use crate::context::ContextMatcher;
+use crate::context::ExitClass;
+use crate::context::ExitMatcherNode;
+use crate::context::RefContext;
 use crate::error::CustomError;
 use crate::error::Res;
 use crate::parser::citation_reference::citation_reference;
 use crate::parser::citation_reference::citation_reference_key;
-use crate::parser::exiting::ExitClass;
-use crate::parser::object::Citation;
 use crate::parser::object_parser::standard_set_object;
-use crate::parser::parser_context::ContextElement;
-use crate::parser::parser_context::ExitMatcherNode;
-use crate::parser::parser_with_context::parser_with_context;
 use crate::parser::util::exit_matcher_parser;
 use crate::parser::util::get_consumed;
-use crate::parser::Object;
+use crate::types::Citation;
+use crate::types::Object;
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-pub fn citation<'r, 's>(
-    context: Context<'r, 's>,
+pub(crate) fn citation<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, Citation<'s>> {
     // TODO: Despite being a standard object, citations cannot exist inside the global prefix/suffix for other citations because citations must contain something that matches @key which is forbidden inside the global prefix/suffix. This TODO is to evaluate if its worth putting in an explicit check for this (which can be easily accomplished by checking the output of `get_bracket_depth()`). I suspect its not worth it because I expect, outside of intentionally crafted inputs, this parser will exit immediately inside a citation since it is unlikely to find the "[cite" substring inside a citation global prefix/suffix.
@@ -48,7 +49,8 @@ pub fn citation<'r, 's>(
         parser_with_context!(global_suffix)(context),
     ))))(remaining)?;
     let (remaining, _) = tag("]")(remaining)?;
-    let (remaining, _) = space0(remaining)?;
+    let (remaining, _trailing_whitespace) =
+        maybe_consume_object_trailing_whitespace_if_not_exiting(context, remaining)?;
     let source = get_consumed(input, remaining);
     Ok((
         remaining,
@@ -59,7 +61,7 @@ pub fn citation<'r, 's>(
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn citestyle<'r, 's>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
+fn citestyle<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
     let (remaining, _) = tuple((tag("/"), style))(input)?;
     let (remaining, _) = opt(tuple((tag("/"), variant)))(remaining)?;
     let source = get_consumed(input, remaining);
@@ -67,30 +69,30 @@ fn citestyle<'r, 's>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>>
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn style<'r, 's>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
+fn style<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
     recognize(many1(verify(anychar, |c| {
         c.is_alphanumeric() || "_-".contains(*c)
     })))(input)
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn variant<'r, 's>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
+fn variant<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
     recognize(many1(verify(anychar, |c| {
         c.is_alphanumeric() || "_-/".contains(*c)
     })))(input)
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn global_prefix<'r, 's>(
-    context: Context<'r, 's>,
+fn global_prefix<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, Vec<Object<'s>>> {
     let exit_with_depth = global_prefix_end(input.get_bracket_depth());
-    let parser_context =
-        context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
-            class: ExitClass::Gamma,
-            exit_matcher: &exit_with_depth,
-        }));
+    let parser_context = ContextElement::ExitMatcherNode(ExitMatcherNode {
+        class: ExitClass::Gamma,
+        exit_matcher: &exit_with_depth,
+    });
+    let parser_context = context.with_additional_node(&parser_context);
     let (remaining, (children, _exit_contents)) = verify(
         many_till(
             parser_with_context!(standard_set_object)(&parser_context),
@@ -102,17 +104,13 @@ fn global_prefix<'r, 's>(
     Ok((remaining, children))
 }
 
-fn global_prefix_end(
-    starting_bracket_depth: BracketDepth,
-) -> impl for<'r, 's> Fn(Context<'r, 's>, OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
-    move |context: Context, input: OrgSource<'_>| {
-        _global_prefix_end(context, input, starting_bracket_depth)
-    }
+fn global_prefix_end(starting_bracket_depth: BracketDepth) -> impl ContextMatcher {
+    move |context, input: OrgSource<'_>| _global_prefix_end(context, input, starting_bracket_depth)
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn _global_prefix_end<'r, 's>(
-    context: Context<'r, 's>,
+fn _global_prefix_end<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
     starting_bracket_depth: BracketDepth,
 ) -> Res<OrgSource<'s>, OrgSource<'s>> {
@@ -134,16 +132,16 @@ fn _global_prefix_end<'r, 's>(
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn global_suffix<'r, 's>(
-    context: Context<'r, 's>,
+fn global_suffix<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, Vec<Object<'s>>> {
     let exit_with_depth = global_suffix_end(input.get_bracket_depth());
-    let parser_context =
-        context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
-            class: ExitClass::Gamma,
-            exit_matcher: &exit_with_depth,
-        }));
+    let parser_context = ContextElement::ExitMatcherNode(ExitMatcherNode {
+        class: ExitClass::Gamma,
+        exit_matcher: &exit_with_depth,
+    });
+    let parser_context = context.with_additional_node(&parser_context);
     let (remaining, (children, _exit_contents)) = verify(
         many_till(
             parser_with_context!(standard_set_object)(&parser_context),
@@ -154,17 +152,13 @@ fn global_suffix<'r, 's>(
     Ok((remaining, children))
 }
 
-fn global_suffix_end(
-    starting_bracket_depth: BracketDepth,
-) -> impl for<'r, 's> Fn(Context<'r, 's>, OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
-    move |context: Context, input: OrgSource<'_>| {
-        _global_suffix_end(context, input, starting_bracket_depth)
-    }
+fn global_suffix_end(starting_bracket_depth: BracketDepth) -> impl ContextMatcher {
+    move |context, input: OrgSource<'_>| _global_suffix_end(context, input, starting_bracket_depth)
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn _global_suffix_end<'r, 's>(
-    context: Context<'r, 's>,
+fn _global_suffix_end<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
     starting_bracket_depth: BracketDepth,
 ) -> Res<OrgSource<'s>, OrgSource<'s>> {
@@ -188,19 +182,23 @@ fn _global_suffix_end<'r, 's>(
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::context::Context;
+    use crate::context::GlobalSettings;
+    use crate::context::List;
     use crate::parser::element_parser::element;
-    use crate::parser::parser_context::ContextTree;
-    use crate::parser::parser_with_context::parser_with_context;
-    use crate::parser::source::Source;
+    use crate::types::Element;
+    use crate::types::Source;
 
     #[test]
     fn citation_simple() {
         let input = OrgSource::new("[cite:@foo]");
-        let initial_context: ContextTree<'_, '_> = ContextTree::new();
+        let global_settings = GlobalSettings::default();
+        let initial_context = ContextElement::document_context();
+        let initial_context = Context::new(&global_settings, List::new(&initial_context));
         let paragraph_matcher = parser_with_context!(element(true))(&initial_context);
         let (remaining, first_paragraph) = paragraph_matcher(input).expect("Parse first paragraph");
         let first_paragraph = match first_paragraph {
-            crate::parser::Element::Paragraph(paragraph) => paragraph,
+            Element::Paragraph(paragraph) => paragraph,
             _ => panic!("Should be a paragraph!"),
         };
         assert_eq!(Into::<&str>::into(remaining), "");

src/parser/citation_reference.rs

@@ -12,24 +12,25 @@ use nom::sequence::tuple;
 
 use super::org_source::BracketDepth;
 use super::org_source::OrgSource;
-use super::Context;
+use crate::context::parser_with_context;
+use crate::context::ContextElement;
+use crate::context::ContextMatcher;
+use crate::context::ExitClass;
+use crate::context::ExitMatcherNode;
+use crate::context::RefContext;
 use crate::error::CustomError;
 use crate::error::MyError;
 use crate::error::Res;
-use crate::parser::exiting::ExitClass;
-use crate::parser::object::CitationReference;
 use crate::parser::object_parser::minimal_set_object;
-use crate::parser::parser_context::ContextElement;
-use crate::parser::parser_context::ExitMatcherNode;
-use crate::parser::parser_with_context::parser_with_context;
 use crate::parser::util::exit_matcher_parser;
 use crate::parser::util::get_consumed;
 use crate::parser::util::WORD_CONSTITUENT_CHARACTERS;
-use crate::parser::Object;
+use crate::types::CitationReference;
+use crate::types::Object;
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-pub fn citation_reference<'r, 's>(
-    context: Context<'r, 's>,
+pub(crate) fn citation_reference<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, CitationReference<'s>> {
     let (remaining, _prefix) =
@@ -48,8 +49,8 @@ pub fn citation_reference<'r, 's>(
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-pub fn citation_reference_key<'r, 's>(
-    context: Context<'r, 's>,
+pub(crate) fn citation_reference_key<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, OrgSource<'s>> {
     let (remaining, source) = recognize(tuple((
@@ -68,16 +69,16 @@ pub fn citation_reference_key<'r, 's>(
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn key_prefix<'r, 's>(
-    context: Context<'r, 's>,
+fn key_prefix<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, Vec<Object<'s>>> {
     let exit_with_depth = key_prefix_end(input.get_bracket_depth());
-    let parser_context =
-        context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
-            class: ExitClass::Gamma,
-            exit_matcher: &exit_with_depth,
-        }));
+    let parser_context = ContextElement::ExitMatcherNode(ExitMatcherNode {
+        class: ExitClass::Gamma,
+        exit_matcher: &exit_with_depth,
+    });
+    let parser_context = context.with_additional_node(&parser_context);
     let (remaining, (children, _exit_contents)) = verify(
         many_till(
             parser_with_context!(minimal_set_object)(&parser_context),
@@ -89,16 +90,16 @@ fn key_prefix<'r, 's>(
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn key_suffix<'r, 's>(
-    context: Context<'r, 's>,
+fn key_suffix<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, Vec<Object<'s>>> {
     let exit_with_depth = key_suffix_end(input.get_bracket_depth());
-    let parser_context =
-        context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
-            class: ExitClass::Gamma,
-            exit_matcher: &exit_with_depth,
-        }));
+    let parser_context = ContextElement::ExitMatcherNode(ExitMatcherNode {
+        class: ExitClass::Gamma,
+        exit_matcher: &exit_with_depth,
+    });
+    let parser_context = context.with_additional_node(&parser_context);
     let (remaining, (children, _exit_contents)) = verify(
         many_till(
             parser_with_context!(minimal_set_object)(&parser_context),
@@ -109,17 +110,13 @@ fn key_suffix<'r, 's>(
     Ok((remaining, children))
 }
 
-fn key_prefix_end(
-    starting_bracket_depth: BracketDepth,
-) -> impl for<'r, 's> Fn(Context<'r, 's>, OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
-    move |context: Context, input: OrgSource<'_>| {
-        _key_prefix_end(context, input, starting_bracket_depth)
-    }
+fn key_prefix_end(starting_bracket_depth: BracketDepth) -> impl ContextMatcher {
+    move |context, input: OrgSource<'_>| _key_prefix_end(context, input, starting_bracket_depth)
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn _key_prefix_end<'r, 's>(
-    context: Context<'r, 's>,
+fn _key_prefix_end<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
     starting_bracket_depth: BracketDepth,
 ) -> Res<OrgSource<'s>, OrgSource<'s>> {
@@ -140,17 +137,13 @@ fn _key_prefix_end<'r, 's>(
     ))(input)
 }
 
-fn key_suffix_end(
-    starting_bracket_depth: BracketDepth,
-) -> impl for<'r, 's> Fn(Context<'r, 's>, OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
-    move |context: Context, input: OrgSource<'_>| {
-        _key_suffix_end(context, input, starting_bracket_depth)
-    }
+fn key_suffix_end(starting_bracket_depth: BracketDepth) -> impl ContextMatcher {
+    move |context, input: OrgSource<'_>| _key_suffix_end(context, input, starting_bracket_depth)
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn _key_suffix_end<'r, 's>(
-    _context: Context<'r, 's>,
+fn _key_suffix_end<'b, 'g, 'r, 's>(
+    _context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
     starting_bracket_depth: BracketDepth,
 ) -> Res<OrgSource<'s>, OrgSource<'s>> {
@@ -168,7 +161,7 @@ fn _key_suffix_end<'r, 's>(
     tag(";")(input)
 }
 
-pub fn must_balance_bracket<'s, F, O>(
+pub(crate) fn must_balance_bracket<'s, F, O>(
     mut inner: F,
 ) -> impl FnMut(OrgSource<'s>) -> Res<OrgSource<'s>, O>
 where

src/parser/clock.rs

@@ -12,16 +12,16 @@ use nom::combinator::verify;
 use nom::sequence::tuple;
 
 use super::org_source::OrgSource;
-use super::Context;
+use crate::context::parser_with_context;
+use crate::context::RefContext;
 use crate::error::Res;
-use crate::parser::parser_with_context::parser_with_context;
 use crate::parser::util::get_consumed;
 use crate::parser::util::start_of_line;
-use crate::parser::Clock;
+use crate::types::Clock;
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-pub fn clock<'r, 's>(
-    context: Context<'r, 's>,
+pub(crate) fn clock<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, Clock<'s>> {
     start_of_line(input)?;
@@ -44,8 +44,8 @@ pub fn clock<'r, 's>(
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn inactive_timestamp_range_duration<'r, 's>(
-    _context: Context<'r, 's>,
+fn inactive_timestamp_range_duration<'b, 'g, 'r, 's>(
+    _context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, OrgSource<'s>> {
     recognize(tuple((
@@ -66,8 +66,8 @@ fn inactive_timestamp_range_duration<'r, 's>(
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn inactive_timestamp<'r, 's>(
-    _context: Context<'r, 's>,
+fn inactive_timestamp<'b, 'g, 'r, 's>(
+    _context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, OrgSource<'s>> {
     recognize(tuple((

src/parser/comment.rs

@@ -13,20 +13,20 @@ use nom::sequence::tuple;
 
 use super::org_source::OrgSource;
 use super::util::get_consumed;
-use super::Context;
+use crate::context::parser_with_context;
+use crate::context::ContextElement;
+use crate::context::RefContext;
 use crate::error::CustomError;
 use crate::error::MyError;
 use crate::error::Res;
-use crate::parser::parser_context::ContextElement;
-use crate::parser::parser_with_context::parser_with_context;
 use crate::parser::util::exit_matcher_parser;
 use crate::parser::util::immediate_in_section;
 use crate::parser::util::start_of_line;
-use crate::parser::Comment;
+use crate::types::Comment;
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-pub fn comment<'r, 's>(
-    context: Context<'r, 's>,
+pub(crate) fn comment<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, Comment<'s>> {
     if immediate_in_section(context, "comment") {
@@ -34,7 +34,8 @@ pub fn comment<'r, 's>(
             "Cannot nest objects of the same element".into(),
         ))));
     }
-    let parser_context = context.with_additional_node(ContextElement::Context("comment"));
+    let parser_context = ContextElement::Context("comment");
+    let parser_context = context.with_additional_node(&parser_context);
     let comment_line_matcher = parser_with_context!(comment_line)(&parser_context);
     let exit_matcher = parser_with_context!(exit_matcher_parser)(&parser_context);
     let (remaining, _first_line) = comment_line_matcher(input)?;
@@ -51,8 +52,8 @@ pub fn comment<'r, 's>(
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn comment_line<'r, 's>(
-    _context: Context<'r, 's>,
+fn comment_line<'b, 'g, 'r, 's>(
+    _context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, OrgSource<'s>> {
     start_of_line(input)?;
@@ -66,11 +67,24 @@ fn comment_line<'r, 's>(
     Ok((remaining, source))
 }
 
+#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
+pub(crate) fn detect_comment<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, ()> {
+    tuple((
+        start_of_line,
+        space0,
+        tag("#"),
+        alt((tag(" "), line_ending, eof)),
+    ))(input)?;
+    Ok((input, ()))
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::parser::parser_context::ContextTree;
-    use crate::parser::parser_with_context::parser_with_context;
+    use crate::context::Context;
+    use crate::context::ContextElement;
+    use crate::context::GlobalSettings;
+    use crate::context::List;
 
     #[test]
     fn require_space_after_hash() {
@@ -79,7 +93,9 @@ mod tests {
 #not a comment
 # Comment again",
         );
-        let initial_context: ContextTree<'_, '_> = ContextTree::new();
+        let global_settings = GlobalSettings::default();
+        let initial_context = ContextElement::document_context();
+        let initial_context = Context::new(&global_settings, List::new(&initial_context));
         let comment_matcher = parser_with_context!(comment)(&initial_context);
         let (remaining, first_comment) = comment_matcher(input).expect("Parse first comment");
         assert_eq!(

src/parser/diary_sexp.rs

@@ -1,31 +1,26 @@
 use nom::branch::alt;
+use nom::bytes::complete::is_not;
 use nom::bytes::complete::tag;
 use nom::character::complete::line_ending;
-use nom::character::complete::space0;
 use nom::combinator::eof;
-use nom::combinator::recognize;
 use nom::sequence::tuple;
 
 use super::org_source::OrgSource;
-use super::sexp::sexp;
-use super::Context;
+use crate::context::RefContext;
 use crate::error::Res;
 use crate::parser::util::get_consumed;
 use crate::parser::util::start_of_line;
-use crate::parser::DiarySexp;
+use crate::types::DiarySexp;
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-pub fn diary_sexp<'r, 's>(
-    _context: Context<'r, 's>,
+pub(crate) fn diary_sexp<'b, 'g, 'r, 's>(
+    _context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, DiarySexp<'s>> {
     start_of_line(input)?;
-    let (remaining, _leading_whitespace) = space0(input)?;
-    let (remaining, _clock) = tag("%%")(remaining)?;
-    let (remaining, _gap_whitespace) = space0(remaining)?;
-    let (remaining, _sexp) = recognize(sexp)(remaining)?;
-    let (remaining, _trailing_whitespace) =
-        recognize(tuple((space0, alt((line_ending, eof)))))(remaining)?;
+    let (remaining, _clock) = tag("%%(")(input)?;
+    let (remaining, _contents) = is_not("\r\n")(remaining)?;
+    let (remaining, _eol) = alt((line_ending, eof))(remaining)?;
 
     let source = get_consumed(input, remaining);
     Ok((
@@ -35,3 +30,9 @@ pub fn diary_sexp<'r, 's>(
         },
     ))
 }
+
+#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
+pub(crate) fn detect_diary_sexp<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, ()> {
+    tuple((start_of_line, tag("%%(")))(input)?;
+    Ok((input, ()))
+}

src/parser/document.rs

@@ -1,112 +1,114 @@
-use nom::branch::alt;
-use nom::bytes::complete::tag;
-use nom::character::complete::anychar;
-use nom::character::complete::line_ending;
-use nom::character::complete::space0;
-use nom::character::complete::space1;
-use nom::combinator::eof;
-use nom::combinator::map;
-use nom::combinator::not;
+use nom::combinator::all_consuming;
 use nom::combinator::opt;
-use nom::combinator::recognize;
-use nom::combinator::verify;
 use nom::multi::many0;
-use nom::multi::many1;
-use nom::multi::many1_count;
-use nom::multi::many_till;
-use nom::multi::separated_list1;
-use nom::sequence::tuple;
 
-use super::element::Element;
-use super::object::Object;
-use super::org_source::convert_error;
+use super::headline::heading;
+use super::in_buffer_settings::apply_in_buffer_settings;
+use super::in_buffer_settings::scan_for_in_buffer_settings;
 use super::org_source::OrgSource;
-use super::parser_with_context::parser_with_context;
-use super::source::Source;
+use super::section::zeroth_section;
 use super::token::AllTokensIterator;
 use super::token::Token;
-use super::util::exit_matcher_parser;
 use super::util::get_consumed;
-use super::util::start_of_line;
-use super::Context;
+use crate::context::parser_with_context;
+use crate::context::Context;
+use crate::context::ContextElement;
+use crate::context::GlobalSettings;
+use crate::context::List;
+use crate::context::RefContext;
+use crate::error::CustomError;
+use crate::error::MyError;
 use crate::error::Res;
-use crate::parser::comment::comment;
-use crate::parser::element_parser::element;
-use crate::parser::exiting::ExitClass;
-use crate::parser::object_parser::standard_set_object;
-use crate::parser::parser_context::ContextElement;
-use crate::parser::parser_context::ContextTree;
-use crate::parser::parser_context::ExitMatcherNode;
-use crate::parser::planning::planning;
-use crate::parser::property_drawer::property_drawer;
+use crate::parser::org_source::convert_error;
 use crate::parser::util::blank_line;
-use crate::parser::util::maybe_consume_trailing_whitespace_if_not_exiting;
+use crate::types::Document;
+use crate::types::Object;
 
-#[derive(Debug)]
-pub struct Document<'s> {
-    pub source: &'s str,
-    pub zeroth_section: Option<Section<'s>>,
-    pub children: Vec<Heading<'s>>,
+/// Parse a full org-mode document.
+///
+/// This is the main entry point for Organic. It will parse the full contents of the input string as an org-mode document.
+#[allow(dead_code)]
+pub fn parse<'s>(input: &'s str) -> Result<Document<'s>, Box<dyn std::error::Error>> {
+    parse_with_settings(input, &GlobalSettings::default())
 }
 
-#[derive(Debug)]
-pub struct Heading<'s> {
-    pub source: &'s str,
-    pub stars: usize,
-    pub todo_keyword: Option<&'s str>,
-    // TODO: add todo-type enum
-    pub title: Vec<Object<'s>>,
-    pub tags: Vec<&'s str>,
-    pub children: Vec<DocumentElement<'s>>,
+/// Parse a full org-mode document with starting settings.
+///
+/// This is the secondary entry point for Organic. It will parse the full contents of the input string as an org-mode document starting with the settings you supplied.
+///
+/// This will not prevent additional settings from being learned during parsing, for example when encountering a "#+TODO".
+#[allow(dead_code)]
+pub fn parse_with_settings<'g, 's>(
+    input: &'s str,
+    global_settings: &'g GlobalSettings<'g, 's>,
+) -> Result<Document<'s>, Box<dyn std::error::Error>> {
+    let initial_context = ContextElement::document_context();
+    let initial_context = Context::new(global_settings, List::new(&initial_context));
+    let wrapped_input = OrgSource::new(input);
+    let ret =
+        all_consuming(parser_with_context!(document_org_source)(&initial_context))(wrapped_input)
+            .map_err(|err| err.to_string())
+            .map(|(_remaining, parsed_document)| parsed_document);
+    Ok(ret?)
 }
 
-#[derive(Debug)]
-pub struct Section<'s> {
-    pub source: &'s str,
-    pub children: Vec<Element<'s>>,
-}
-
-#[derive(Debug)]
-pub enum DocumentElement<'s> {
-    Heading(Heading<'s>),
-    Section(Section<'s>),
-}
-
-impl<'s> Source<'s> for Document<'s> {
-    fn get_source(&'s self) -> &'s str {
-        self.source
-    }
-}
-
-impl<'s> Source<'s> for DocumentElement<'s> {
-    fn get_source(&'s self) -> &'s str {
-        match self {
-            DocumentElement::Heading(obj) => obj.source,
-            DocumentElement::Section(obj) => obj.source,
-        }
-    }
-}
-
-impl<'s> Source<'s> for Section<'s> {
-    fn get_source(&'s self) -> &'s str {
-        self.source
-    }
-}
-
-impl<'s> Source<'s> for Heading<'s> {
-    fn get_source(&'s self) -> &'s str {
-        self.source
-    }
+/// Parse a full org-mode document.
+///
+/// Use this entry point when you want to have direct control over the starting context or if you want to use this integrated with other nom parsers. For general-purpose usage, the `parse` and `parse_with_settings` functions are a lot simpler.
+///
+/// This will not prevent additional settings from being learned during parsing, for example when encountering a "#+TODO".
+#[allow(dead_code)]
+fn document<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
+    input: &'s str,
+) -> Res<&'s str, Document<'s>> {
+    let (remaining, doc) = document_org_source(context, input.into()).map_err(convert_error)?;
+    Ok((Into::<&str>::into(remaining), doc))
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
 #[allow(dead_code)]
-pub fn document(input: &str) -> Res<&str, Document> {
-    let initial_context: ContextTree<'_, '_> = ContextTree::new();
-    let wrapped_input = OrgSource::new(input);
-    let (remaining, document) = _document(&initial_context, wrapped_input)
-        .map(|(rem, out)| (Into::<&str>::into(rem), out))
-        .map_err(convert_error)?;
+fn document_org_source<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
+    input: OrgSource<'s>,
+) -> Res<OrgSource<'s>, Document<'s>> {
+    let mut final_settings = Vec::new();
+    let (_, document_settings) = scan_for_in_buffer_settings(input)?;
+    let setup_files: Vec<String> = document_settings
+        .iter()
+        .filter(|kw| kw.key.eq_ignore_ascii_case("setupfile"))
+        .map(|kw| kw.value)
+        .map(|setup_file| {
+            context
+                .get_global_settings()
+                .file_access
+                .read_file(setup_file)
+                .map_err(|err| nom::Err::<CustomError<OrgSource<'_>>>::Failure(err.into()))
+        })
+        .collect::<Result<Vec<_>, _>>()?;
+    for setup_file in setup_files.iter().map(String::as_str) {
+        let (_, setup_file_settings) =
+            scan_for_in_buffer_settings(setup_file.into()).map_err(|_err| {
+                nom::Err::Error(CustomError::MyError(MyError(
+                    "TODO: make this take an owned string so I can dump err.to_string() into it."
+                        .into(),
+                )))
+            })?;
+        final_settings.extend(setup_file_settings);
+    }
+    final_settings.extend(document_settings);
+    let new_settings = apply_in_buffer_settings(final_settings, context.get_global_settings())
+        .map_err(|_err| {
+            nom::Err::Error(CustomError::MyError(MyError(
+                "TODO: make this take an owned string so I can dump err.to_string() into it."
+                    .into(),
+            )))
+        })?;
+    let new_context = context.with_global_settings(&new_settings);
+    let context = &new_context;
+
+    let (remaining, document) =
+        _document(context, input).map(|(rem, out)| (Into::<&str>::into(rem), out))?;
     {
         // If there are radio targets in this document then we need to parse the entire document again with the knowledge of the radio targets.
         let all_radio_targets: Vec<&Vec<Object<'_>>> = document
@@ -122,11 +124,11 @@ pub fn document(input: &str) -> Res<&str, Document> {
             .map(|rt| &rt.children)
             .collect();
         if !all_radio_targets.is_empty() {
-            let initial_context = initial_context
-                .with_additional_node(ContextElement::RadioTarget(all_radio_targets));
-            let (remaining, document) = _document(&initial_context, wrapped_input)
-                .map(|(rem, out)| (Into::<&str>::into(rem), out))
-                .map_err(convert_error)?;
+            let mut new_global_settings = context.get_global_settings().clone();
+            new_global_settings.radio_targets = all_radio_targets;
+            let parser_context = context.with_global_settings(&new_global_settings);
+            let (remaining, document) = _document(&parser_context, input)
+                .map(|(rem, out)| (Into::<&str>::into(rem), out))?;
             return Ok((remaining.into(), document));
         }
     }
@@ -134,8 +136,8 @@ pub fn document(input: &str) -> Res<&str, Document> {
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn _document<'r, 's>(
-    context: Context<'r, 's>,
+fn _document<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, Document<'s>> {
     let zeroth_section_matcher = parser_with_context!(zeroth_section)(context);
@@ -154,259 +156,8 @@ fn _document<'r, 's>(
     ))
 }
 
-#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn zeroth_section<'r, 's>(
-    context: Context<'r, 's>,
-    input: OrgSource<'s>,
-) -> Res<OrgSource<'s>, Section<'s>> {
-    // TODO: The zeroth section is specialized so it probably needs its own parser
-    let parser_context = context
-        .with_additional_node(ContextElement::ConsumeTrailingWhitespace(true))
-        .with_additional_node(ContextElement::Context("section"))
-        .with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
-            class: ExitClass::Document,
-            exit_matcher: &section_end,
-        }));
-    let without_consuming_whitespace_context =
-        parser_context.with_additional_node(ContextElement::ConsumeTrailingWhitespace(false));
-
-    let element_matcher = parser_with_context!(element(true))(&parser_context);
-    let exit_matcher = parser_with_context!(exit_matcher_parser)(&parser_context);
-
-    let (remaining, comment_and_property_drawer_element) = opt(tuple((
-        opt(parser_with_context!(comment)(
-            &without_consuming_whitespace_context,
-        )),
-        parser_with_context!(property_drawer)(context),
-        many0(blank_line),
-    )))(input)?;
-
-    let (remaining, (mut children, _exit_contents)) = verify(
-        many_till(element_matcher, exit_matcher),
-        |(children, _exit_contents)| {
-            !children.is_empty() || comment_and_property_drawer_element.is_some()
-        },
-    )(remaining)?;
-
-    comment_and_property_drawer_element.map(|(comment, property_drawer, _ws)| {
-        children.insert(0, Element::PropertyDrawer(property_drawer));
-        comment
-            .map(Element::Comment)
-            .map(|ele| children.insert(0, ele));
-    });
-
-    let (remaining, _trailing_ws) =
-        maybe_consume_trailing_whitespace_if_not_exiting(context, remaining)?;
-
-    let source = get_consumed(input, remaining);
-    Ok((
-        remaining,
-        Section {
-            source: source.into(),
-            children,
-        },
-    ))
-}
-
-#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn section<'r, 's>(
-    context: Context<'r, 's>,
-    mut input: OrgSource<'s>,
-) -> Res<OrgSource<'s>, Section<'s>> {
-    // TODO: The zeroth section is specialized so it probably needs its own parser
-    let parser_context = context
-        .with_additional_node(ContextElement::ConsumeTrailingWhitespace(true))
-        .with_additional_node(ContextElement::Context("section"))
-        .with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
-            class: ExitClass::Document,
-            exit_matcher: &section_end,
-        }));
-    let element_matcher = parser_with_context!(element(true))(&parser_context);
-    let exit_matcher = parser_with_context!(exit_matcher_parser)(&parser_context);
-    let (mut remaining, (planning_element, property_drawer_element)) = tuple((
-        opt(parser_with_context!(planning)(&parser_context)),
-        opt(parser_with_context!(property_drawer)(&parser_context)),
-    ))(input)?;
-    if planning_element.is_none() && property_drawer_element.is_none() {
-        let (remain, _ws) = many0(blank_line)(remaining)?;
-        remaining = remain;
-        input = remain;
-    }
-    let (remaining, (mut children, _exit_contents)) = verify(
-        many_till(element_matcher, exit_matcher),
-        |(children, _exit_contents)| {
-            !children.is_empty() || property_drawer_element.is_some() || planning_element.is_some()
-        },
-    )(remaining)?;
-    property_drawer_element
-        .map(Element::PropertyDrawer)
-        .map(|ele| children.insert(0, ele));
-    planning_element
-        .map(Element::Planning)
-        .map(|ele| children.insert(0, ele));
-
-    let (remaining, _trailing_ws) =
-        maybe_consume_trailing_whitespace_if_not_exiting(context, remaining)?;
-
-    let source = get_consumed(input, remaining);
-    Ok((
-        remaining,
-        Section {
-            source: source.into(),
-            children,
-        },
-    ))
-}
-
-#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn section_end<'r, 's>(
-    _context: Context<'r, 's>,
-    input: OrgSource<'s>,
-) -> Res<OrgSource<'s>, OrgSource<'s>> {
-    recognize(detect_headline)(input)
-}
-
-const fn heading(
-    parent_stars: usize,
-) -> impl for<'r, 's> Fn(Context<'r, 's>, OrgSource<'s>) -> Res<OrgSource<'s>, Heading<'s>> {
-    move |context: Context, input: OrgSource<'_>| _heading(context, input, parent_stars)
-}
-
-#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn _heading<'r, 's>(
-    context: Context<'r, 's>,
-    input: OrgSource<'s>,
-    parent_stars: usize,
-) -> Res<OrgSource<'s>, Heading<'s>> {
-    not(|i| context.check_exit_matcher(i))(input)?;
-    let (remaining, (star_count, _ws, maybe_todo_keyword, title, heading_tags)) =
-        headline(context, input, parent_stars)?;
-    let section_matcher = parser_with_context!(section)(context);
-    let heading_matcher = parser_with_context!(heading(star_count))(context);
-    let (remaining, maybe_section) =
-        opt(map(section_matcher, DocumentElement::Section))(remaining)?;
-    let (remaining, mut children) =
-        many0(map(heading_matcher, DocumentElement::Heading))(remaining)?;
-    if let Some(section) = maybe_section {
-        children.insert(0, section);
-    }
-    let remaining = if children.is_empty() {
-        // Support empty headings
-        let (remain, _ws) = many0(blank_line)(remaining)?;
-        remain
-    } else {
-        remaining
-    };
-
-    let source = get_consumed(input, remaining);
-    Ok((
-        remaining,
-        Heading {
-            source: source.into(),
-            stars: star_count,
-            todo_keyword: maybe_todo_keyword
-                .map(|(todo_keyword, _ws)| Into::<&str>::into(todo_keyword)),
-            title,
-            tags: heading_tags,
-            children,
-        },
-    ))
-}
-
-#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn detect_headline<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, ()> {
-    tuple((start_of_line, many1(tag("*")), space1))(input)?;
-    Ok((input, ()))
-}
-
-#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn headline<'r, 's>(
-    context: Context<'r, 's>,
-    input: OrgSource<'s>,
-    parent_stars: usize,
-) -> Res<
-    OrgSource<'s>,
-    (
-        usize,
-        OrgSource<'s>,
-        Option<(OrgSource<'s>, OrgSource<'s>)>,
-        Vec<Object<'s>>,
-        Vec<&'s str>,
-    ),
-> {
-    let parser_context =
-        context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
-            class: ExitClass::Document,
-            exit_matcher: &headline_title_end,
-        }));
-    let standard_set_object_matcher = parser_with_context!(standard_set_object)(&parser_context);
-
-    let (
-        remaining,
-        (_sol, star_count, ws, maybe_todo_keyword, title, maybe_tags, _ws, _line_ending),
-    ) = tuple((
-        start_of_line,
-        verify(many1_count(tag("*")), |star_count| {
-            *star_count > parent_stars
-        }),
-        space1,
-        opt(tuple((heading_keyword, space1))),
-        many1(standard_set_object_matcher),
-        opt(tuple((space0, tags))),
-        space0,
-        alt((line_ending, eof)),
-    ))(input)?;
-    Ok((
-        remaining,
-        (
-            star_count,
-            ws,
-            maybe_todo_keyword,
-            title,
-            maybe_tags
-                .map(|(_ws, tags)| {
-                    tags.into_iter()
-                        .map(|single_tag| Into::<&str>::into(single_tag))
-                        .collect()
-                })
-                .unwrap_or(Vec::new()),
-        ),
-    ))
-}
-
-#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn headline_title_end<'r, 's>(
-    _context: Context<'r, 's>,
-    input: OrgSource<'s>,
-) -> Res<OrgSource<'s>, OrgSource<'s>> {
-    recognize(tuple((
-        opt(tuple((space0, tags, space0))),
-        alt((line_ending, eof)),
-    )))(input)
-}
-
-#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn tags<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, Vec<OrgSource<'s>>> {
-    let (remaining, (_open, tags, _close)) =
-        tuple((tag(":"), separated_list1(tag(":"), single_tag), tag(":")))(input)?;
-    Ok((remaining, tags))
-}
-
-#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn single_tag<'r, 's>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
-    recognize(many1(verify(anychar, |c| {
-        c.is_alphanumeric() || "_@#%".contains(*c)
-    })))(input)
-}
-
-#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn heading_keyword<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
-    // TODO: This should take into account the value of "#+TODO:" ref https://orgmode.org/manual/Per_002dfile-keywords.html and possibly the configurable variable org-todo-keywords ref https://orgmode.org/manual/Workflow-states.html. Case is significant.
-    alt((tag("TODO"), tag("DONE")))(input)
-}
-
 impl<'s> Document<'s> {
-    pub fn iter_tokens<'r>(&'r self) -> impl Iterator<Item = Token<'r, 's>> {
+    fn iter_tokens<'r>(&'r self) -> impl Iterator<Item = Token<'r, 's>> {
         AllTokensIterator::new(Token::Document(self))
     }
 }

src/parser/drawer.rs

@@ -11,29 +11,29 @@ use nom::multi::many_till;
 use nom::sequence::tuple;
 
 use super::org_source::OrgSource;
-use super::Context;
+use crate::context::parser_with_context;
+use crate::context::ContextElement;
+use crate::context::ExitClass;
+use crate::context::ExitMatcherNode;
+use crate::context::RefContext;
 use crate::error::CustomError;
 use crate::error::MyError;
 use crate::error::Res;
 use crate::parser::element_parser::element;
-use crate::parser::exiting::ExitClass;
-use crate::parser::parser_context::ContextElement;
-use crate::parser::parser_context::ExitMatcherNode;
-use crate::parser::parser_with_context::parser_with_context;
-use crate::parser::source::SetSource;
 use crate::parser::util::blank_line;
 use crate::parser::util::exit_matcher_parser;
 use crate::parser::util::get_consumed;
 use crate::parser::util::immediate_in_section;
 use crate::parser::util::start_of_line;
 use crate::parser::util::WORD_CONSTITUENT_CHARACTERS;
-use crate::parser::Drawer;
-use crate::parser::Element;
-use crate::parser::Paragraph;
+use crate::types::Drawer;
+use crate::types::Element;
+use crate::types::Paragraph;
+use crate::types::SetSource;
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-pub fn drawer<'r, 's>(
-    context: Context<'r, 's>,
+pub(crate) fn drawer<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, Drawer<'s>> {
     if immediate_in_section(context, "drawer") {
@@ -50,13 +50,17 @@ pub fn drawer<'r, 's>(
         recognize(tuple((space0, line_ending))),
     ))(remaining)?;
 
-    let parser_context = context
-        .with_additional_node(ContextElement::ConsumeTrailingWhitespace(true))
-        .with_additional_node(ContextElement::Context("drawer"))
-        .with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
+    let contexts = [
+        ContextElement::ConsumeTrailingWhitespace(true),
+        ContextElement::Context("drawer"),
+        ContextElement::ExitMatcherNode(ExitMatcherNode {
             class: ExitClass::Alpha,
             exit_matcher: &drawer_end,
-        }));
+        }),
+    ];
+    let parser_context = context.with_additional_node(&contexts[0]);
+    let parser_context = parser_context.with_additional_node(&contexts[1]);
+    let parser_context = parser_context.with_additional_node(&contexts[2]);
 
     let element_matcher = parser_with_context!(element(true))(&parser_context);
     let exit_matcher = parser_with_context!(exit_matcher_parser)(&parser_context);
@@ -98,8 +102,8 @@ fn name<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn drawer_end<'r, 's>(
-    _context: Context<'r, 's>,
+fn drawer_end<'b, 'g, 'r, 's>(
+    _context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, OrgSource<'s>> {
     start_of_line(input)?;

src/parser/dynamic_block.rs

@@ -1,39 +1,43 @@
 use nom::branch::alt;
 use nom::bytes::complete::is_not;
+use nom::bytes::complete::tag;
 use nom::bytes::complete::tag_no_case;
 use nom::character::complete::line_ending;
 use nom::character::complete::space0;
 use nom::character::complete::space1;
+use nom::combinator::consumed;
 use nom::combinator::eof;
 use nom::combinator::not;
 use nom::combinator::opt;
 use nom::combinator::recognize;
+use nom::multi::many0;
 use nom::multi::many_till;
+use nom::sequence::preceded;
 use nom::sequence::tuple;
 
 use super::org_source::OrgSource;
-use super::Context;
+use crate::context::parser_with_context;
+use crate::context::ContextElement;
+use crate::context::ExitClass;
+use crate::context::ExitMatcherNode;
+use crate::context::RefContext;
 use crate::error::CustomError;
 use crate::error::MyError;
 use crate::error::Res;
 use crate::parser::element_parser::element;
-use crate::parser::exiting::ExitClass;
-use crate::parser::greater_element::DynamicBlock;
-use crate::parser::lesser_element::Paragraph;
-use crate::parser::parser_context::ContextElement;
-use crate::parser::parser_context::ExitMatcherNode;
-use crate::parser::parser_with_context::parser_with_context;
-use crate::parser::source::SetSource;
 use crate::parser::util::blank_line;
 use crate::parser::util::exit_matcher_parser;
 use crate::parser::util::get_consumed;
 use crate::parser::util::immediate_in_section;
 use crate::parser::util::start_of_line;
-use crate::parser::Element;
+use crate::types::DynamicBlock;
+use crate::types::Element;
+use crate::types::Paragraph;
+use crate::types::SetSource;
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-pub fn dynamic_block<'r, 's>(
-    context: Context<'r, 's>,
+pub(crate) fn dynamic_block<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, DynamicBlock<'s>> {
     // TODO: Do I need to differentiate between different dynamic block types.
@@ -50,37 +54,40 @@ pub fn dynamic_block<'r, 's>(
         opt(tuple((space1, parameters))),
         line_ending,
     ))(remaining)?;
-    let parser_context = context
-        .with_additional_node(ContextElement::ConsumeTrailingWhitespace(true))
-        .with_additional_node(ContextElement::Context("dynamic block"))
-        .with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
+    let contexts = [
+        ContextElement::ConsumeTrailingWhitespace(true),
+        ContextElement::Context("dynamic block"),
+        ContextElement::ExitMatcherNode(ExitMatcherNode {
             class: ExitClass::Alpha,
             exit_matcher: &dynamic_block_end,
-        }));
+        }),
+    ];
+    let parser_context = context.with_additional_node(&contexts[0]);
+    let parser_context = parser_context.with_additional_node(&contexts[1]);
+    let parser_context = parser_context.with_additional_node(&contexts[2]);
     let parameters = match parameters {
         Some((_ws, parameters)) => Some(parameters),
         None => None,
     };
     let element_matcher = parser_with_context!(element(true))(&parser_context);
     let exit_matcher = parser_with_context!(exit_matcher_parser)(&parser_context);
-    let (remaining, children) = match tuple((
-        not(exit_matcher),
+    not(exit_matcher)(remaining)?;
+    let (remaining, leading_blank_lines) = opt(consumed(tuple((
         blank_line,
-        many_till(blank_line, exit_matcher),
-    ))(remaining)
-    {
-        Ok((remain, (_not_immediate_exit, first_line, (_trailing_whitespace, _exit_contents)))) => {
+        many0(preceded(not(exit_matcher), blank_line)),
+    ))))(remaining)?;
+    let leading_blank_lines =
+        leading_blank_lines.map(|(source, (first_line, _remaining_lines))| {
             let mut element = Element::Paragraph(Paragraph::of_text(first_line.into()));
-            let source = get_consumed(remaining, remain);
             element.set_source(source.into());
-            (remain, vec![element])
-        }
-        Err(_) => {
-            let (remaining, (children, _exit_contents)) =
-                many_till(element_matcher, exit_matcher)(remaining)?;
-            (remaining, children)
-        }
-    };
+            element
+        });
+    let (remaining, (mut children, _exit_contents)) =
+        many_till(element_matcher, exit_matcher)(remaining)?;
+    if let Some(lines) = leading_blank_lines {
+        children.insert(0, lines);
+    }
+
     let (remaining, _end) = dynamic_block_end(&parser_context, remaining)?;
 
     let source = get_consumed(input, remaining);
@@ -106,14 +113,15 @@ fn parameters<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn dynamic_block_end<'r, 's>(
-    _context: Context<'r, 's>,
+fn dynamic_block_end<'b, 'g, 'r, 's>(
+    _context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
 ) -> Res<OrgSource<'s>, OrgSource<'s>> {
     start_of_line(input)?;
     let (remaining, source) = recognize(tuple((
         space0,
-        tag_no_case("#+end:"),
+        tag_no_case("#+end"),
+        opt(tag(":")),
         alt((eof, line_ending)),
     )))(input)?;
     Ok((remaining, source))

src/parser/element_parser.rs

@@ -4,15 +4,19 @@ use nom::multi::many0;
 
 use super::clock::clock;
 use super::comment::comment;
+use super::comment::detect_comment;
+use super::diary_sexp::detect_diary_sexp;
 use super::diary_sexp::diary_sexp;
 use super::drawer::drawer;
 use super::dynamic_block::dynamic_block;
-use super::element::Element;
+use super::fixed_width_area::detect_fixed_width_area;
 use super::fixed_width_area::fixed_width_area;
+use super::footnote_definition::detect_footnote_definition;
 use super::footnote_definition::footnote_definition;
 use super::greater_block::greater_block;
 use super::horizontal_rule::horizontal_rule;
 use super::keyword::affiliated_keyword;
+use super::keyword::babel_call_keyword;
 use super::keyword::keyword;
 use super::latex_environment::latex_environment;
 use super::lesser_block::comment_block;
@@ -24,25 +28,30 @@ use super::org_source::OrgSource;
 use super::paragraph::paragraph;
 use super::plain_list::detect_plain_list;
 use super::plain_list::plain_list;
-use super::source::SetSource;
+use super::table::detect_table;
 use super::util::get_consumed;
 use super::util::maybe_consume_trailing_whitespace_if_not_exiting;
-use super::Context;
+use crate::context::parser_with_context;
+use crate::context::RefContext;
 use crate::error::CustomError;
 use crate::error::MyError;
 use crate::error::Res;
-use crate::parser::parser_with_context::parser_with_context;
 use crate::parser::table::org_mode_table;
+use crate::types::Element;
+use crate::types::SetSource;
 
-pub const fn element(
+pub(crate) const fn element(
     can_be_paragraph: bool,
-) -> impl for<'r, 's> Fn(Context<'r, 's>, OrgSource<'s>) -> Res<OrgSource<'s>, Element<'s>> {
-    move |context: Context, input: OrgSource<'_>| _element(context, input, can_be_paragraph)
+) -> impl for<'b, 'g, 'r, 's> Fn(
+    RefContext<'b, 'g, 'r, 's>,
+    OrgSource<'s>,
+) -> Res<OrgSource<'s>, Element<'s>> {
+    move |context, input: OrgSource<'_>| _element(context, input, can_be_paragraph)
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn _element<'r, 's>(
-    context: Context<'r, 's>,
+fn _element<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
     can_be_paragraph: bool,
 ) -> Res<OrgSource<'s>, Element<'s>> {
@@ -64,6 +73,7 @@ fn _element<'r, 's>(
     let horizontal_rule_matcher = parser_with_context!(horizontal_rule)(context);
     let keyword_matcher = parser_with_context!(keyword)(context);
     let affiliated_keyword_matcher = parser_with_context!(affiliated_keyword)(context);
+    let babel_keyword_matcher = parser_with_context!(babel_call_keyword)(context);
     let paragraph_matcher = parser_with_context!(paragraph)(context);
     let latex_environment_matcher = parser_with_context!(latex_environment)(context);
 
@@ -87,6 +97,7 @@ fn _element<'r, 's>(
         map(fixed_width_area_matcher, Element::FixedWidthArea),
         map(horizontal_rule_matcher, Element::HorizontalRule),
         map(latex_environment_matcher, Element::LatexEnvironment),
+        map(babel_keyword_matcher, Element::BabelCall),
         map(keyword_matcher, Element::Keyword),
     ))(remaining)
     {
@@ -116,19 +127,29 @@ fn _element<'r, 's>(
     Ok((remaining, element))
 }
 
-pub const fn detect_element(
+pub(crate) const fn detect_element(
     can_be_paragraph: bool,
-) -> impl for<'r, 's> Fn(Context<'r, 's>, OrgSource<'s>) -> Res<OrgSource<'s>, ()> {
-    move |context: Context, input: OrgSource<'_>| _detect_element(context, input, can_be_paragraph)
+) -> impl for<'b, 'g, 'r, 's> Fn(RefContext<'b, 'g, 'r, 's>, OrgSource<'s>) -> Res<OrgSource<'s>, ()>
+{
+    move |context, input: OrgSource<'_>| _detect_element(context, input, can_be_paragraph)
 }
 
 #[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
-fn _detect_element<'r, 's>(
-    context: Context<'r, 's>,
+fn _detect_element<'b, 'g, 'r, 's>(
+    context: RefContext<'b, 'g, 'r, 's>,
     input: OrgSource<'s>,
     can_be_paragraph: bool,
 ) -> Res<OrgSource<'s>, ()> {
-    if detect_plain_list(context, input).is_ok() {
+    if alt((
+        parser_with_context!(detect_plain_list)(context),
+        detect_footnote_definition,
+        detect_diary_sexp,
+        detect_comment,
+        detect_fixed_width_area,
+        detect_table,
+    ))(input)
+    .is_ok()
+    {
         return Ok((input, ()));
     }
     if _element(context, input, can_be_paragraph).is_ok() {