Publish version 0.1.8.

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

.dockerignore

@@ -1,3 +1,4 @@
 **/.git
 target
 Cargo.lock
+notes/

.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-build.yaml

@@ -0,0 +1,244 @@
+apiVersion: tekton.dev/v1beta1
+kind: PipelineRun
+metadata:
+  name: rust-build
+spec:
+  pipelineSpec:
+    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: 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: $(params.path-to-dockerfile)
+          - name: BUILDER_IMAGE
+            value: "gcr.io/kaniko-project/executor:v1.12.1"
+          - name: EXTRA_ARGS
+            value:
+              - --cache=true
+              - --cache-copy-layers
+              - --cache-repo=harbor.fizz.buzz/kanikocache/cache
+              - --use-new-run # Should result in a speed-up
+              - --reproducible # To remove timestamps so layer caching works.
+              - --snapshot-mode=redo
+              - --skip-unused-stages=true
+              - --registry-mirror=dockerhub.dockerhub.svc.cluster.local
+        workspaces:
+          - name: source
+            workspace: git-source
+          - name: dockerconfig
+            workspace: docker-credentials
+        runAfter:
+          - fetch-repository
+      - name: run-image-none
+        taskRef:
+          name: run-docker-image
+        workspaces:
+          - name: source
+            workspace: git-source
+          - name: cargo-cache
+            workspace: cargo-cache
+        runAfter:
+          - build-image
+        params:
+          - name: args
+            value: ["--no-default-features"]
+          - name: docker-image
+            value: "$(params.image-name):$(tasks.fetch-repository.results.commit)"
+      - name: run-image-tracing
+        taskRef:
+          name: run-docker-image
+        workspaces:
+          - name: source
+            workspace: git-source
+          - name: cargo-cache
+            workspace: cargo-cache
+        runAfter:
+          - run-image-none
+        params:
+          - name: args
+            value: ["--no-default-features", "--features", "tracing"]
+          - name: docker-image
+            value: "$(params.image-name):$(tasks.fetch-repository.results.commit)"
+      - name: run-image-compare
+        taskRef:
+          name: run-docker-image
+        workspaces:
+          - name: source
+            workspace: git-source
+          - name: cargo-cache
+            workspace: cargo-cache
+        runAfter:
+          - run-image-tracing
+        params:
+          - name: args
+            value: ["--no-default-features", "--features", "compare"]
+          - name: docker-image
+            value: "$(params.image-name):$(tasks.fetch-repository.results.commit)"
+      - name: run-image-default
+        taskRef:
+          name: run-docker-image
+        workspaces:
+          - name: source
+            workspace: git-source
+          - name: cargo-cache
+            workspace: cargo-cache
+        runAfter:
+          - run-image-compare
+        params:
+          - name: args
+            value: []
+          - name: docker-image
+            value: "$(params.image-name):$(tasks.fetch-repository.results.commit)"
+      - name: run-image-all
+        taskRef:
+          name: run-docker-image
+        workspaces:
+          - name: source
+            workspace: git-source
+          - name: cargo-cache
+            workspace: cargo-cache
+        runAfter:
+          - run-image-default
+        params:
+          - name: args
+            value: ["--no-default-features", "--features", "tracing,compare"]
+          - name: docker-image
+            value: "$(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-build
+    - name: docker-credentials
+      secret:
+        secretName: harbor-plain
+  serviceAccountName: build-bot
+  timeout: 240h0m0s
+  params:
+    - name: image-name
+      value: "harbor.fizz.buzz/private/organic-build"
+    - name: path-to-image-context
+      value: docker/organic_build/
+    - name: path-to-dockerfile
+      value: docker/organic_build/Dockerfile

.lighthouse/pipeline-rust-test.yaml

@@ -4,6 +4,10 @@ metadata:
   name: rust-test
 spec:
   pipelineSpec:
+    timeouts:
+      pipeline: "2h0m0s"
+      tasks: "1h0m40s"
+      finally: "0h30m0s"
     params:
       - name: image-name
         description: The name for the built image
@@ -14,14 +18,6 @@ spec:
       - name: path-to-dockerfile
         description: The path to the Dockerfile
         type: string
-      - name: command
-        type: array
-        description: Command to run.
-        default: []
-      - name: args
-        type: array
-        description: Arguments passed to command.
-        default: []
     tasks:
       - name: do-stuff
         taskSpec:
@@ -87,6 +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
@@ -113,10 +110,17 @@ spec:
         runAfter:
           - build-image
         params:
-          - name: command
-            value: ["$(params.command[*])"]
           - name: args
-            value: ["$(params.args[*])"]
+            value:
+              [
+                --no-default-features,
+                --features,
+                compare,
+                --no-fail-fast,
+                --lib,
+                --test,
+                test_loader,
+              ]
           - name: docker-image
             value: "$(params.image-name):$(tasks.fetch-repository.results.commit)"
     finally:
@@ -201,7 +205,6 @@ spec:
       secret:
         secretName: harbor-plain
   serviceAccountName: build-bot
-  timeout: 240h0m0s
   params:
     - name: image-name
       value: "harbor.fizz.buzz/private/organic-test"
@@ -209,7 +212,3 @@ spec:
       value: docker/organic_test/
     - name: path-to-dockerfile
       value: docker/organic_test/Dockerfile
-    - name: command
-      value: [cargo, test]
-    - name: args
-      value: [--lib, --test, test_loader]

.lighthouse/pipeline-rustfmt.yaml

@@ -14,14 +14,6 @@ spec:
       - name: path-to-dockerfile
         description: The path to the Dockerfile
         type: string
-      - name: rustfmt-command
-        type: array
-        description: Command to run rustfmt.
-        default: []
-      - name: rustfmt-args
-        type: array
-        description: Arguments passed to rustfmt.
-        default: []
       - name: GIT_USER_NAME
         description: The username for git
         type: string
@@ -81,14 +73,6 @@ spec:
             value: $(params.PULL_BASE_SHA)
           - name: deleteExisting
             value: "true"
-      - name: detect-tag
-        taskRef:
-          name: detect-tag
-        workspaces:
-          - name: repo
-            workspace: git-source
-        runAfter:
-          - fetch-repository
       - name: build-image
         taskRef:
           name: kaniko
@@ -118,7 +102,6 @@ spec:
             workspace: docker-credentials
         runAfter:
           - fetch-repository
-          - detect-tag
       - name: rustfmt
         taskRef:
           name: run-docker-image
@@ -128,10 +111,6 @@ spec:
         runAfter:
           - build-image
         params:
-          - name: command
-            value: ["$(params.rustfmt-command[*])"]
-          - name: args
-            value: ["$(params.rustfmt-args[*])"]
           - name: docker-image
             value: "$(params.image-name):$(tasks.fetch-repository.results.commit)"
       - name: cargo-fix
@@ -249,7 +228,3 @@ spec:
       value: docker/cargo_fmt/
     - name: path-to-dockerfile
       value: docker/cargo_fmt/Dockerfile
-    - name: command
-      value: [cargo, fmt]
-    - name: args
-      value: []

.lighthouse/triggers.yaml

@@ -16,3 +16,17 @@ 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.
+      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]+$"

Cargo.toml

@@ -1,38 +1,62 @@
 [package]
 name = "organic"
-version = "0.1.0"
+version = "0.1.8"
 authors = ["Tom Alexander <tom@fizz.buzz>"]
 description = "An org-mode parser."
 edition = "2021"
 license = "0BSD"
 repository = "https://code.fizz.buzz/talexander/organic"
-readme = "README.org"
+readme = "README.md"
 keywords = ["emacs", "org-mode"]
-categories = ["template-engine"]
+categories = ["parsing"]
+resolver = "2"
+include = [
+  "LICENSE",
+  "**/*.rs",
+  "Cargo.toml"
+]
 
 [lib]
 name = "organic"
 path = "src/lib.rs"
 
 [[bin]]
-name = "toy"
-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"
-opentelemetry = "0.17.0"
-opentelemetry-jaeger = "0.16.0"
-tracing = "0.1.37"
-tracing-opentelemetry = "0.17.2"
-tracing-subscriber = {version="0.3.16", features=["env-filter"]}
+opentelemetry = { version = "0.20.0", optional = true, default-features = false, features = ["trace", "rt-tokio"] }
+opentelemetry-otlp = { version = "0.13.0", optional = true }
+opentelemetry-semantic-conventions = { version = "0.12.0", optional = true }
+tokio = { version = "1.30.0", optional = true, default-features = false, features = ["rt", "rt-multi-thread"] }
+tracing = { version = "0.1.37", optional = true }
+tracing-opentelemetry = { version = "0.20.0", optional = true }
+tracing-subscriber = { version = "0.3.17", optional = true, features = ["env-filter"] }
 
 [build-dependencies]
 walkdir = "2.3.3"
 
 [features]
-default = ["compare"]
+default = []
 compare = []
+tracing = ["dep:opentelemetry", "dep:opentelemetry-otlp", "dep:opentelemetry-semantic-conventions", "dep:tokio", "dep:tracing", "dep:tracing-opentelemetry", "dep:tracing-subscriber"]
 
-[profile.release]
+# Optimized build for any sort of release.
+[profile.release-lto]
+inherits = "release"
 lto = true
 strip = "symbols"
+
+# Profile for performance testing with the "perf" tool. Notably keeps debug enabled and does not strip symbols to make reading the perf output easier.
+[profile.perf]
+inherits = "release"
+lto = true
+debug = true

Makefile

@@ -33,29 +33,42 @@ release:
 clean:
 > cargo clean
 
+.PHONY: format
+format:
+> $(MAKE) -C docker/cargo_fmt run
+
 .PHONY: test
 test:
-> cargo test --lib --test test_loader -- --test-threads $(TESTJOBS)
+> cargo test --no-default-features --features compare --no-fail-fast --lib --test test_loader -- --test-threads $(TESTJOBS)
+
+.PHONY: dockertest
+dockertest:
+> $(MAKE) -C docker/organic_test
+> 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:
+# Delete volumes created for running the tests in docker. This does not touch anything related to the jaeger docker container.
+> docker volume rm cargo-cache rust-cache
 
 .PHONY: integrationtest
 integrationtest:
-> cargo test --no-fail-fast --test test_loader -- --test-threads $(TESTJOBS)
+> cargo test --no-default-features --features compare --no-fail-fast --test test_loader -- --test-threads $(TESTJOBS)
 
 .PHONY: unittest
 unittest:
-> cargo test --lib -- --test-threads $(TESTJOBS)
-
-.PHONY: run
-run:
-> cargo run
-
-.PHONY: debug
-debug:
-> RUST_LOG=debug cargo run
+> cargo test --no-default-features --lib -- --test-threads $(TESTJOBS)
 
 .PHONY: jaeger
 jaeger:
-> docker run -d --rm --name toylanguagedocker -p 6831:6831/udp -p 6832:6832/udp -p 16686:16686 -p 14268:14268 jaegertracing/all-in-one:latest
+# 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 --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:
@@ -63,4 +76,4 @@ jaegerweb:
 
 .PHONY: jaegerstop
 jaegerstop:
-> docker stop toylanguagedocker
+> docker stop organicdocker

README.md

@@ -0,0 +1,64 @@
+# Organic - Free Range Org-Mode
+
+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), 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.

README.org

@@ -1,10 +0,0 @@
-#+options: toc:nil
-#+title: Organic - Free Range Org-Mode
-
-Organic is an emacs-less implementation of an [[https://orgmode.org/][org-mode]] parser.
-
-* Project Status
-This project is a personal learning project to grow my experience in [[https://www.rust-lang.org/][rust]]. 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.
-
-* License
-This project is released under the public-domain-equivalent [[https://www.tldrlegal.com/license/bsd-0-clause-license][0BSD 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.

build.rs

@@ -1,15 +1,24 @@
+#[cfg(feature = "compare")]
 use std::env;
+#[cfg(feature = "compare")]
 use std::fs::File;
+#[cfg(feature = "compare")]
 use std::io::Write;
+#[cfg(feature = "compare")]
 use std::path::Path;
 
+#[cfg(feature = "compare")]
 use walkdir::WalkDir;
 
+#[cfg(feature = "compare")]
 fn main() {
     let out_dir = env::var("OUT_DIR").unwrap();
     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")
@@ -31,6 +40,10 @@ fn main() {
     }
 }
 
+#[cfg(not(feature = "compare"))]
+fn main() {}
+
+#[cfg(feature = "compare")]
 fn write_test(test_file: &mut File, test: &walkdir::DirEntry) {
     let test_name = test
         .path()
@@ -41,6 +54,7 @@ fn write_test(test_file: &mut File, test: &walkdir::DirEntry) {
         .strip_suffix(".org")
         .expect("Should have .org extension")
         .replace("/", "_");
+    let test_name = format!("autogen_{}", test_name);
 
     if let Some(_reason) = is_expect_fail(test_name.as_str()) {
         write!(test_file, "#[ignore]\n").unwrap();
@@ -54,27 +68,23 @@ fn write_test(test_file: &mut File, test: &walkdir::DirEntry) {
     .unwrap();
 }
 
+#[cfg(feature = "compare")]
 fn write_header(test_file: &mut File) {
     write!(
         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;
 
 "#
     )
     .unwrap();
 }
 
+#[cfg(feature = "compare")]
 fn is_expect_fail(name: &str) -> Option<&str> {
     match name {
-        "drawer_drawer_with_headline_inside" => Some("Apparently lines with :end: become their own paragraph. This odd behavior needs to be investigated more."),
-        "element_container_priority_footnote_definition_dynamic_block" => Some("Apparently broken begin lines become their own paragraph."),
-        "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."),
-        "export_snippet_paragraph_break_precedent" => Some("Emacs 28 has broken behavior so the tests in the CI fail."),
+        "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."),
         _ => 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:
@@ -26,10 +26,11 @@ else
 	@echo "REMOTE_REPO not defined, not removing from remote repo."
 endif
 
+# NOTE: This target will write to folders underneath the git-root
 .PHONY: run
-run:
-	docker run --rm -i -t $(IMAGE_NAME)
+run: build
+	docker run --rm --init --read-only --mount type=tmpfs,destination=/tmp -v "$$(readlink -f ../../):/source" --workdir=/source $(IMAGE_NAME)
 
 .PHONY: shell
-shell:
-	docker run --rm -i -t --entrypoint /bin/bash $(IMAGE_NAME)
+shell: build
+	docker run --rm -i -t --entrypoint /bin/sh --mount type=tmpfs,destination=/tmp -v "$$(readlink -f ../../):/source" --workdir=/source $(IMAGE_NAME)

docker/organic_build/Dockerfile

@@ -0,0 +1,6 @@
+FROM rustlang/rust:nightly-alpine3.17
+
+RUN apk add --no-cache musl-dev
+RUN cargo install --locked --no-default-features --features ci-autoclean cargo-cache
+
+ENTRYPOINT ["cargo", "build"]

docker/organic_build/Makefile

@@ -0,0 +1,37 @@
+IMAGE_NAME:=organic-build
+# REMOTE_REPO:=harbor.fizz.buzz/private
+
+.PHONY: all
+all: build push
+
+.PHONY: build
+build:
+	docker build -t $(IMAGE_NAME) -f Dockerfile .
+
+.PHONY: push
+push:
+ifdef REMOTE_REPO
+	docker tag $(IMAGE_NAME) $(REMOTE_REPO)/$(IMAGE_NAME)
+	docker push $(REMOTE_REPO)/$(IMAGE_NAME)
+else
+	@echo "REMOTE_REPO not defined, not pushing to a remote repo."
+endif
+
+.PHONY: clean
+clean:
+	docker rmi $(IMAGE_NAME)
+ifdef REMOTE_REPO
+	docker rmi $(REMOTE_REPO)/$(IMAGE_NAME)
+else
+	@echo "REMOTE_REPO not defined, not removing from remote repo."
+endif
+	docker volume rm cargo-cache
+
+# NOTE: This target will write to folders underneath the git-root
+.PHONY: run
+run: build
+	docker run --rm --init --read-only --mount type=tmpfs,destination=/tmp -v "$$(readlink -f ../../):/source" --workdir=/source --mount source=cargo-cache,target=/usr/local/cargo/registry $(IMAGE_NAME)
+
+.PHONY: shell
+shell: build
+	docker run --rm -i -t --entrypoint /bin/sh --mount type=tmpfs,destination=/tmp -v "$$(readlink -f ../../):/source" --workdir=/source --mount source=cargo-cache,target=/usr/local/cargo/registry $(IMAGE_NAME)

docker/organic_test/Dockerfile

@@ -1,4 +1,107 @@
-FROM rustlang/rust:nightly-alpine3.17
+FROM alpine:3.17 AS build
+RUN apk add --no-cache build-base musl-dev git autoconf make texinfo gnutls-dev ncurses-dev gawk libgccjit-dev
 
-RUN apk add --no-cache musl-dev emacs
+
+FROM build AS build-emacs
+ARG EMACS_VERSION=emacs-29.1
+RUN git clone --depth 1 --branch $EMACS_VERSION https://git.savannah.gnu.org/git/emacs.git /root/emacs
+WORKDIR /root/emacs
+RUN mkdir /root/dist
+RUN ./autogen.sh
+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=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.
+RUN git clone https://git.savannah.gnu.org/git/emacs/org-mode.git /root/org-mode && git -C /root/org-mode checkout $ORG_VERSION
+# RUN mkdir /root/org-mode && git -C /root/org-mode init --initial-branch=main && git -C /root/org-mode remote add origin https://git.savannah.gnu.org/git/emacs/org-mode.git && git -C /root/org-mode fetch origin $ORG_VERSION && git -C /root/org-mode checkout FETCH_HEAD
+WORKDIR /root/org-mode
+RUN make compile
+RUN make DESTDIR="/root/dist" install
+
+
+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:
@@ -25,11 +29,16 @@ ifdef REMOTE_REPO
 else
 	@echo "REMOTE_REPO not defined, not removing from remote repo."
 endif
+	docker volume rm rust-cache cargo-cache
 
 .PHONY: run
-run:
-	docker run --rm -i -t $(IMAGE_NAME)
+run: build
+	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:
-	docker run --rm -i -t --entrypoint /bin/bash $(IMAGE_NAME)
+shell: build
+	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 "$all_status"
+}
+
+main "${@}"

elisp_snippets/README.md

@@ -0,0 +1 @@
+This folder is for snippets of elisp that are useful for development.

elisp_snippets/dump_org_element_affiliated_keywords.el

@@ -0,0 +1,3 @@
+(dolist (var org-element-affiliated-keywords)
+  (message "\"%s\"," (downcase var))
+  )

elisp_snippets/dump_org_entities.el

@@ -0,0 +1,5 @@
+(dolist (var org-entities)
+  (when (listp var)
+      (message "\"%s\"," (nth 0 var))
+    )
+  )

notes/exit_matcher_loop_notes.txt

@@ -1,35 +0,0 @@
-Headings add exit matcher for heading
-
-Paragraphs add exit matcher for elements (but it should be sans paragraph)
-
-
-
-
-* foo
-* bar
-* baz
-
-context tree -> ()
-
-match * foo
-
-context tree -> exit(heading matcher)
-
-check exit
-invoke heading matcher
-check exit
-invoke heading matcher
-check exit
-invoke heading matcher
-adds second heading matcher exit
-
-
-Ways around this:
-- Always parse SOMETHING before checking for exit
-  - Doesn't always seem possible
-- Disable exit matchers during exit check
-  - Seems like it would break syntax
-- Have separate parsers for the beginning of the exit condition (for example, checking for just the headline instead of the full heading parser)
-  - Won't be possible with paragraphs ending at any other element
-- Check exit matchers in parent parser
-  - Will this work? seems like it would just create larger loops

notes/optimization_ideas.org

@@ -0,0 +1,28 @@
+* Analysis
+** Parse start per character
+It might help analysis to record how often we start a specific type of parse for each character. For example, at the start of a plain list, if we had a count of how often each character was the start of a parse of a list we could use that to see how often that list is getting re-parsed.
+* Optimizations
+** Edit whitespace for list items
+Whether or not a list item owns the trailing whitespace depends on if it is the last list item in that list. Since we do not know ahead of time if an item is the last item in the list, we have to either re-parse the list item or modify it after parsing.
+
+*** For
+We already are modifying the source of some elements after-the-fact with src_rust{set_source()} so this would be more of the same.
+*** Against
+I'd like to phase out such modifications because they seem hacky and fragile.
+** Make detect element function
+Some exit matchers are based on when the next element is found. Some elements do not need to be fully parsed to identify that they are a valid element. For example, src_org{1. foo} can already be identified as the start of a plain list (in the right context) without needing to parse the entire element.
+*** For
+Avoiding parsing the entire element for an exit matcher would reduce redundant parses.
+*** Against
+This adds code complexity and introduces the potential for bugs.
+
+How many elements can be reasonably early-detected? For example, src_org{#+begin_src foo} is not enough to detect the start of a source block because without the src_org{#+end_src} it is just plain text.
+** Grab multiple characters in plaintext parser before checking exit matcher
+Currently we check the exit matcher after each character inside the plain text parser (and many others). Are there character sequences we can assume no exit matcher will trigger between? For example, a contiguous string of latin-alphabet letters?
+*** For
+This could significantly reduce our calls to exit matchers.
+*** Against
+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/element_container_priority/plain_list_greater_block.org

@@ -1,6 +1,7 @@
-1. foo
+1. plain-list
    #+begin_center
 
 
    #+end_center
-2. bar
+
+   Is this still in the plain list?

org_mode_samples/exit_matcher_investigation/README.txt

@@ -1 +0,0 @@
-This folder is an investigation into whether or not my exit matchers should operate from the top down or bottom up.

org_mode_samples/exit_matcher_investigation/bold_with_asterisk_inside.org

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

org_mode_samples/exit_matcher_investigation/list_paragraph_nesting.README.txt

@@ -1,3 +0,0 @@
-Looks like 2 blank lines always exits the top-level plain list.
-
-Plain lists do not seem to go inside paragraphs but rather exist beside them.

org_mode_samples/exit_matcher_investigation/list_paragraph_nesting.org

@@ -1,12 +0,0 @@
-1. foo
-
-   bar
-
-   1. baz
-
-      lorem
-
-   ipsum
-
-
-dolar

org_mode_samples/exit_matcher_investigation/table_list.README.txt

@@ -1 +0,0 @@
-Looks like table cells cannot contain lists but can contain bolds

org_mode_samples/exit_matcher_investigation/table_list.org

@@ -1,5 +0,0 @@
-ip *su* m
-
-| foo      | bar |
-|----------+-----|
-| 1. lo *re* m |     |

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/dynamic_block/simple.org

@@ -0,0 +1,25 @@
+#+BEGIN: clocktable :scope file :maxlevel 2
+#+CAPTION: Clock summary at [2023-08-25 Fri 05:34]
+| Headline     | Time   |
+|--------------+--------|
+| *Total time* | *0:00* |
+#+END:
+
+#+BEGIN: columnview :hlines 1 :id global
+| ITEM  | TODO | PRIORITY | TAGS                         |
+|-------+------+----------+------------------------------|
+| Foo   |      | B        |                              |
+|-------+------+----------+------------------------------|
+| Bar   | TODO | B        |                              |
+|-------+------+----------+------------------------------|
+| Baz   |      | B        | :thisisatag:                 |
+| Lorem |      | B        | :thisshouldinheritfromabove: |
+| Ipsum |      | B        | :multiple:tags:              |
+#+END:
+* Foo
+* TODO Bar
+* Baz :thisisatag:
+** Lorem :thisshouldinheritfromabove:
+*** Ipsum                                                   :multiple:tags:
+* Dolar ::
+* cat :dog: bat

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/content_on_next_line.org

@@ -0,0 +1,7 @@
+1. foo
+2.
+     bar
+   1.
+       #+begin_center
+Still in the list
+       #+end_center

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_eof.org

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

org_mode_samples/greater_element/plain_list/description_list.org

@@ -0,0 +1,11 @@
+- foo :: bar
+- cat    ::
+  dog
+- lorem
+  :: ipsum
+-
+  lorem :: ipsum
+- dolar *bold* foo :: ipsum
+- big gap ::
+
+  stuff

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

@@ -0,0 +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/plain_list/trailing_whitespace_ownership_test_case_1.org

@@ -0,0 +1,9 @@
+1. foo
+
+   1. bar
+
+   2. baz
+
+2. lorem
+
+ipsum

org_mode_samples/greater_element/plain_list/trailing_whitespace_ownership_test_case_2.org

@@ -0,0 +1,11 @@
+1. foo
+
+   1. bar
+
+   2. baz
+
+   cat
+
+2. lorem
+
+ipsum

org_mode_samples/greater_element/plain_list/trailing_whitespace_ownership_test_case_3.org

@@ -0,0 +1,10 @@
+1. cat
+   1. foo
+
+      1. bar
+
+      2. baz
+
+   2. lorem
+
+ipsum

org_mode_samples/greater_element/plain_list/trailing_whitespace_ownership_test_case_4.org

@@ -0,0 +1,12 @@
+1. cat
+   1. foo
+
+      1. bar
+
+      2. baz
+
+   2. lorem
+
+2. dog
+
+ipsum

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/property_drawer/properties_with_underscore.org

@@ -0,0 +1,7 @@
+** foo
+:PROPERTIES:
+:DESCRIPTION: lorem
+:ALT_TITLE: ipsum
+:END:
+
+bar

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/floating_affiliated_keyword.org

@@ -0,0 +1,15 @@
+#+name: foo
+#+caption: bar
+#+caption: baz
+
+[[file:lorem/ipsum.png]]
+
+#+name: cat
+#+foo: dog
+[[file:lorem/ipsum.png]]
+
+#+name: cat
+#+foo: dog
+
+
+foo

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