103 Commits

Author SHA1 Message Date
Tom Alexander
fcd63b1231 fixup
All checks were successful
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-31 21:58:41 -04:00
Tom Alexander
743b4c9982 fixup
All checks were successful
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-31 21:55:20 -04:00
Tom Alexander
7eccf8fccd Remove dependency on run-docker-image task.
Some checks failed
rust-test Build rust-test has failed
rust-build Build rust-build has succeeded
2023-08-31 21:48:06 -04:00
Tom Alexander
a40a504f94 Switch to using read-only root in docker containers.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-31 21:23:51 -04:00
Tom Alexander
80d77ff5d6 Fix handling of unicode in compare tests.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-31 20:20:00 -04:00
Tom Alexander
ee92049e5d Merge branch 'special_block'
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-31 19:19:29 -04:00
Tom Alexander
510985e97c Fix greater blocks by preventing nesting even if they are not the immediate parent. 2023-08-31 19:17:46 -04:00
Tom Alexander
949d0989f4 Add a test showing the current parser is broken with deeply nested greater blocks. 2023-08-31 19:15:28 -04:00
Tom Alexander
2a4d22bdd4 Add test for nesting of greater blocks.
This shows that greater blocks of different types can be directly nested even if they are both special blocks (as long as they are different special blocks).
2023-08-31 19:09:38 -04:00
Tom Alexander
7a903acedc Support special blocks in compare. 2023-08-31 19:04:44 -04:00
Tom Alexander
5171326d63 Create a test for special blocks. 2023-08-31 19:02:18 -04:00
Tom Alexander
67f79aeb51 Remove context from detect plain list.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-31 18:53:28 -04:00
Tom Alexander
b2383d9f93 Fix footnote definition performance.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
We were re-parsing each footnote definition in the footnote definition exit matcher which causes their contents to get re-parsed. This compounds with long lists of footnote definitions.
2023-08-31 18:47:23 -04:00
Tom Alexander
9e2a323f6f Merge branch 'trailing_whitespace_at_end_of_file'
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-31 17:29:52 -04:00
Tom Alexander
0fcb3f73f9 Move handling of contentless item to handle contentless description item. 2023-08-31 17:25:42 -04:00
Tom Alexander
bfc9e7f58d When re-parsing last item in list, only disable white space consumption for last element in item. 2023-08-31 17:08:21 -04:00
Tom Alexander
b5f0521b56 Only consume trailing whitespace when not exiting for all objects. 2023-08-31 15:45:31 -04:00
Tom Alexander
2048d8f0b6 Support comments at the end of the line in diary sexp.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-31 15:31:54 -04:00
Tom Alexander
466716881e Fix macros consuming whitespace even when the exit matcher is calling for an exit.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-31 15:11:29 -04:00
Tom Alexander
eb9c582fa5 '>' is allowed as a post character in text markup.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-29 23:57:15 -04:00
Tom Alexander
214e895d85 Support backslash at the end of a macro. 2023-08-29 23:42:16 -04:00
Tom Alexander
db3086743c Publish version 0.1.4.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-29 23:28:17 -04:00
Tom Alexander
207a0546b0 Run full test suite despite default feature selection.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-29 23:23:31 -04:00
Tom Alexander
e9480fd156 Disable the compare tests when the compare feature is disabled.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-29 23:17:46 -04:00
Tom Alexander
28aca041f7 Publish version 0.1.3.
Some checks failed
rustfmt Build rustfmt has failed
rust-test Build rust-test has failed
rust-build Build rust-build has succeeded
2023-08-29 23:05:36 -04:00
Tom Alexander
d82def2a70 Merge branch 'compare_improvements'
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-29 22:58:42 -04:00
Tom Alexander
d471f7178b Wrap the components of headlines in diff layers. 2023-08-29 22:57:08 -04:00
Tom Alexander
2c5c26c55f Allow diff layers that are not associated with tokens. 2023-08-29 22:47:40 -04:00
Tom Alexander
7944659802 Compare headline level. 2023-08-29 22:11:56 -04:00
Tom Alexander
58aca53144 Move get_property into util. 2023-08-29 22:07:23 -04:00
Tom Alexander
6f2d90162b Do not use the plain text parser for property drawers.
This additional exit condition was causing property drawers to parse incorrectly.
2023-08-29 22:03:20 -04:00
Tom Alexander
f170a557ed Use character offsets in diff. 2023-08-29 21:49:16 -04:00
Tom Alexander
eaa38ce772 Include an error message for failed bounds checking.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-29 21:27:54 -04:00
Tom Alexander
a6d742a536 Fix handling line breaks after divider in description lists. 2023-08-29 21:27:54 -04:00
Tom Alexander
45be9e7bde Merge branch 'description_list'
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-29 19:36:45 -04:00
Tom Alexander
f6c895319f Add support for diffing description lists. 2023-08-29 19:35:54 -04:00
Tom Alexander
2682779534 Add support for parsing description lists. 2023-08-29 18:13:55 -04:00
Tom Alexander
b48d472546 Fix build.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-29 18:07:35 -04:00
Tom Alexander
ea6faf728c Add test for description list. 2023-08-29 18:07:35 -04:00
Tom Alexander
f4ea1b7303 Merge branch 'accuracy_fixes_from_feeding_large_documents'
Some checks failed
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has failed
2023-08-29 17:49:19 -04:00
Tom Alexander
80b55fdd45 Consume trailing whitespace for macro. 2023-08-29 17:42:58 -04:00
Tom Alexander
f426e32798 Do not include trailing punctuation or whitespace in plain links. 2023-08-29 17:35:04 -04:00
Tom Alexander
66037356c5 Add test showing plain links ending in punctuation currently do not parse correctly. 2023-08-29 17:24:44 -04:00
Tom Alexander
1bcd1895c0 Allow affiliating keywords with regular keywords. 2023-08-29 17:19:13 -04:00
Tom Alexander
e3d38cfbe2 Add a test for floating affiliated keywords. 2023-08-29 17:05:19 -04:00
Tom Alexander
2ba0dc49be Support export affiliated keywords. 2023-08-29 17:01:35 -04:00
Tom Alexander
9df40fb13f Only allow specific keywords for affiliated keywords. 2023-08-29 16:56:07 -04:00
Tom Alexander
cc671925db Support empty sections under headings. 2023-08-29 16:07:43 -04:00
Tom Alexander
950baa9d5d Only allow a single section under a heading. 2023-08-29 16:03:13 -04:00
Tom Alexander
56865c68fc Do not allow plain links without a path. 2023-08-29 15:44:04 -04:00
Tom Alexander
f592b73ae7 Merge branch 'reduce_context_usage_in_exit_matchers'
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-29 15:17:16 -04:00
Tom Alexander
3206027b96 Add all entities. 2023-08-29 15:16:22 -04:00
Tom Alexander
3e6df7ba78 Print character offset from rust's parse perspective during compare. 2023-08-29 14:40:58 -04:00
Tom Alexander
ac313d093e Improve error handling in compare. 2023-08-29 14:20:53 -04:00
Tom Alexander
f376f1cf8e Add a test for empty sections. 2023-08-29 14:10:26 -04:00
Tom Alexander
f21385a901 Add a helper function for logging during debugging.
All checks were successful
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-29 14:03:14 -04:00
Tom Alexander
1d06d95bb1 Add a minimum stars figure to heading parser to reduce re-parses. 2023-08-29 14:01:28 -04:00
Tom Alexander
bfc88c1d1b Use a detect_headline function instead of the full headline parse for the section_end exit matcher.
This shaved 2 seconds off the first 800 lines of org-mode/doc/org-guide.org.
2023-08-29 11:35:54 -04:00
Tom Alexander
f29720e5b9 Switch to using a type for bracket depth.
This is to make changing the type easier in the future.
2023-08-29 11:18:15 -04:00
Tom Alexander
27a9b5aeb1 Switch to i16 for backet depth count.
This is having a measurable performance increase. 32k bracket depth should be enough for any non-malicious document.
2023-08-29 11:14:50 -04:00
Tom Alexander
8051c3d2b7 Remove line number tracking.
The documentation was incorrect, none of the org-mode elements have a line number restriction for their contents.
2023-08-29 11:09:28 -04:00
Tom Alexander
bd97d2f69d Switch to i32 for tracking bracket depth. 2023-08-29 11:07:00 -04:00
Tom Alexander
14b1d0526c Manually implement Debug and make convert_error more generic.
All checks were successful
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-29 10:58:05 -04:00
Tom Alexander
288350daef Iterate over the bytes instead of characters when counting brackets.
All checks were successful
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-28 03:52:21 -04:00
Tom Alexander
c683516620 Switch inline source blocks to using bracket depth from OrgSource instead of from the context.
This is for the same reasons as footnote references.
2023-08-28 03:04:33 -04:00
Tom Alexander
e731e8ff6b Switch inline babel call to using bracket depth from OrgSource instead of from the context.
This is for the same reasons as footnote references.
2023-08-28 03:04:33 -04:00
Tom Alexander
4c2037ec44 Switch subscript and superscript to using bracket depth from OrgSource instead of from the context.
This is for the same reasons as footnote references.
2023-08-28 03:04:33 -04:00
Tom Alexander
a46b358549 Switch citations to using bracket depth from OrgSource instead of from the context.
This is for the same reasons as footnote references.
2023-08-28 03:04:32 -04:00
Tom Alexander
ec813e3b3f Switch to using bracket depth from OrgSource instead of from the context for footnote references.
It is currently unknown if this will produce a performance increase, but unless it has a significant performance penalty we are going to go forward with this change because it makes it more explicit which values need to be read deeply from other elements (therefore needing to be in the context) vs values that can be bound to the exit matcher since they are only used within the confines of the current element.

I suspect we will get a performance boost since it will be reducing the nodes that need to be walked in the context but maintaining bracket depth count over the entire document instead of only inside elements that need balanced brackets could cost us.
2023-08-28 03:04:32 -04:00
Tom Alexander
f11f7bcc73 Keep track of bracket, brace, and parenthesis depth when iterating over the OrgSource. 2023-08-28 01:18:46 -04:00
Tom Alexander
9e0e5f6f0a Remove line number limit for LaTeX fragments. 2023-08-28 01:18:46 -04:00
Tom Alexander
16e788c36c Add tests for LaTeX fragments and text markup that span more than three lines.
The documentation currently states that the body for these cannot span more than three lines but that is not the behavior I am seeing from emacs in practice. Waiting on a mailing list response to tell me if this is a documentation error or a parser error.
2023-08-28 01:18:46 -04:00
Tom Alexander
b35d785e73 Fix tracing in the run_docker_compare.bash script.
Some checks failed
rust-build Build rust-build has failed
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
2023-08-28 01:18:45 -04:00
Tom Alexander
1952d175c0 Record line number in OrgSource.
This will be used for elements who have limits on the number of lines inside of them. This includes LaTeX fragment bodies and text markup.
2023-08-28 01:18:45 -04:00
Tom Alexander
20c17c40be Switch greater blocks to using name provided when building exit matcher instead of from context. 2023-08-28 01:18:45 -04:00
Tom Alexander
b6b869df25 Minor improvement to error message in diff.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-28 01:05:09 -04:00
Tom Alexander
18a396b7cb Remove deprecated tests.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-27 23:25:50 -04:00
Tom Alexander
085490476e Fix make dockertest.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-27 22:41:55 -04:00
Tom Alexander
9c9964c66f Add lt and gt entities.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-27 22:15:23 -04:00
Tom Alexander
1a3e26c148 Update plain list greater block exit matcher priority test to match blog post.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
It is still testing the same thing, but I changed the contents a bit to match what is being used in my blog post.
2023-08-27 21:03:16 -04:00
Tom Alexander
e9e6a8ff64 Merge branch 'clean_up_docker'
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-27 18:03:51 -04:00
Tom Alexander
b124317f30 Fix up scripts to handle the changes to the docker containers. 2023-08-27 18:03:37 -04:00
Tom Alexander
ad389f0776 Remove volumes in the clean step.
All checks were successful
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-27 17:53:51 -04:00
Tom Alexander
75dfc7f812 Depend on build when using the docker images. 2023-08-27 17:51:57 -04:00
Tom Alexander
c17de8ef5e Set up the same mounts when running make shell. 2023-08-27 17:50:33 -04:00
Tom Alexander
378b6bb391 Update the run targets for the Makefiles for the docker containers.
This was previously using the standard docker makefile I use as a starting point for all of my docker makefiles. Now it will properly mount the source directory.
2023-08-27 17:46:36 -04:00
Tom Alexander
cc86591a6c Support the debug/dev profile in the perf script.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-27 17:02:12 -04:00
Tom Alexander
f25dbc1d7c Add a script for testing organic parse times.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
This is not meant to produce publishable or comparable benchmarks. Such a script would have to run many iterations with the input already loaded into memory, proper prioritization via nice/ionice, and have a warm-up phase. This is just automating a basic test I am frequently running to compare parse times when investigating performance issues.
2023-08-27 16:56:32 -04:00
Tom Alexander
daee50c160 Merge branch 'dynamic_block_test'
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-27 16:23:28 -04:00
Tom Alexander
3e143796f7 Compare heading todo keywords.
All checks were successful
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
This only handles the default case where the only valid TODO keywords are TODO and DONE.
2023-08-27 15:56:08 -04:00
Tom Alexander
9cc5e63c1b Compare heading tags.
Some checks failed
rust-test Build rust-test has failed
rust-build Build rust-build has succeeded
2023-08-25 07:05:59 -04:00
Tom Alexander
be6197e4c7 Store the tags in the heading. 2023-08-25 06:20:06 -04:00
Tom Alexander
2d4e54845b Add support for parsing tags in headlines. 2023-08-25 06:13:29 -04:00
Tom Alexander
d5ea650b96 Add a test for dynamic blocks. 2023-08-25 05:36:57 -04:00
Tom Alexander
60363579b5 Merge branch 'plain_list_content_on_next_line'
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-25 05:28:14 -04:00
Tom Alexander
1b678fe81f Add tests for detect_plain_list. 2023-08-25 05:27:09 -04:00
Tom Alexander
bfea828e62 Update detect_plain_list to support line breaks. 2023-08-25 05:27:08 -04:00
Tom Alexander
bc5745a95f Add support for list items with a line break before their contents. 2023-08-25 05:18:26 -04:00
Tom Alexander
efa372a9e9 Add a test case that breaks the current parser. 2023-08-25 04:39:58 -04:00
Tom Alexander
2fb57daaec Move the table cell object parser into the object parser file.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-25 04:35:54 -04:00
Tom Alexander
3a38f4cd35 Add support for the ast entity.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-25 04:28:24 -04:00
Tom Alexander
45e16fea2d Honor the NO_COLOR environment variable.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-25 04:25:39 -04:00
Tom Alexander
5134cece7b Add color to compare output.
All checks were successful
rustfmt Build rustfmt has succeeded
rust-test Build rust-test has succeeded
rust-build Build rust-build has succeeded
2023-08-25 04:09:52 -04:00
86 changed files with 2958 additions and 1252 deletions

View File

@@ -14,10 +14,6 @@ spec:
- name: path-to-dockerfile
description: The path to the Dockerfile
type: string
- name: command
type: array
description: Command to run.
default: []
tasks:
- name: report-pending
taskRef:
@@ -92,8 +88,6 @@ spec:
runAfter:
- build-image
params:
- name: command
value: ["$(params.command[*])"]
- name: args
value: ["--no-default-features"]
- name: docker-image
@@ -109,8 +103,6 @@ spec:
runAfter:
- run-image-none
params:
- name: command
value: ["$(params.command[*])"]
- name: args
value: ["--no-default-features", "--features", "tracing"]
- name: docker-image
@@ -126,8 +118,6 @@ spec:
runAfter:
- run-image-tracing
params:
- name: command
value: ["$(params.command[*])"]
- name: args
value: ["--no-default-features", "--features", "compare"]
- name: docker-image
@@ -143,8 +133,6 @@ spec:
runAfter:
- run-image-compare
params:
- name: command
value: ["$(params.command[*])"]
- name: args
value: []
- name: docker-image
@@ -160,8 +148,6 @@ spec:
runAfter:
- run-image-default
params:
- name: command
value: ["$(params.command[*])"]
- name: args
value: ["--no-default-features", "--features", "tracing,compare"]
- name: docker-image
@@ -256,5 +242,3 @@ spec:
value: docker/organic_build/
- name: path-to-dockerfile
value: docker/organic_build/Dockerfile
- name: command
value: [cargo, build]

View File

@@ -18,14 +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:
@@ -107,22 +99,41 @@ spec:
runAfter:
- fetch-repository
- name: run-image
taskRef:
name: run-docker-image
taskSpec:
metadata: {}
stepTemplate:
name: ""
workingDir: "$(workspaces.source.path)"
workspaces:
- name: source
mountPath: /source
- name: cargo-cache
mountPath: /usr/local/cargo/registry
optional: true
steps:
- name: run
image: "$(params.IMAGE)"
command: []
args:
[
--no-default-features,
--features,
compare,
--no-fail-fast,
--lib,
--test,
test_loader,
]
workspaces:
- name: source
workspace: git-source
- name: cargo-cache
workspace: cargo-cache
params:
- name: IMAGE
value: "$(params.image-name):$(tasks.fetch-repository.results.commit)"
runAfter:
- build-image
params:
- name: command
value: ["$(params.command[*])"]
- name: args
value: ["$(params.args[*])"]
- name: docker-image
value: "$(params.image-name):$(tasks.fetch-repository.results.commit)"
finally:
- name: report-success
when:
@@ -212,7 +223,3 @@ 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]

View File

@@ -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
@@ -119,10 +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
@@ -240,7 +228,3 @@ spec:
value: docker/cargo_fmt/
- name: path-to-dockerfile
value: docker/cargo_fmt/Dockerfile
- name: command
value: [cargo, fmt]
- name: args
value: []

View File

@@ -1,6 +1,6 @@
[package]
name = "organic"
version = "0.1.2"
version = "0.1.4"
authors = ["Tom Alexander <tom@fizz.buzz>"]
description = "An org-mode parser."
edition = "2021"
@@ -13,8 +13,7 @@ resolver = "2"
include = [
"LICENSE",
"**/*.rs",
"Cargo.toml",
"tests/*"
"Cargo.toml"
]
[lib]
@@ -40,15 +39,17 @@ tracing-subscriber = { version = "0.3.17", optional = true, features = ["env-fil
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"]
# 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

View File

@@ -35,12 +35,12 @@ clean:
.PHONY: test
test:
> cargo test --no-fail-fast --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 -v "$$(readlink -f ./):/source:ro" --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target -w /source organic-test cargo test --no-fail-fast --lib --test test_loader -- --test-threads $(TESTJOBS)
> docker run --init --rm -i -t --read-only -v "$$(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: dockerclean
dockerclean:
@@ -49,18 +49,18 @@ dockerclean:
.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)
> cargo test --no-default-features --lib -- --test-threads $(TESTJOBS)
.PHONY: jaeger
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:

View File

@@ -1,10 +1,16 @@
#[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");
@@ -31,6 +37,10 @@ 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()
@@ -55,6 +65,7 @@ fn write_test(test_file: &mut File, test: &walkdir::DirEntry) {
.unwrap();
}
#[cfg(feature = "compare")]
fn write_header(test_file: &mut File) {
write!(
test_file,
@@ -70,6 +81,7 @@ use organic::parser::sexp::sexp_with_padding;
.unwrap();
}
#[cfg(feature = "compare")]
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."),

View File

@@ -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)

View File

@@ -2,3 +2,5 @@ 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"]

View File

@@ -25,11 +25,13 @@ ifdef REMOTE_REPO
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:
docker run --rm -i -t $(IMAGE_NAME)
run: build
docker run --rm --init --read-only --mount type=tmpfs,destination=/tmp -v "$$(readlink -f ../../):/source" --workdir=/source --mount source=cargo-cache,target=/usr/local/cargo/registry $(IMAGE_NAME)
.PHONY: shell
shell:
docker run --rm -i -t --entrypoint /bin/bash $(IMAGE_NAME)
shell: build
docker run --rm -i -t --entrypoint /bin/sh --mount type=tmpfs,destination=/tmp -v "$$(readlink -f ../../):/source" --workdir=/source --mount source=cargo-cache,target=/usr/local/cargo/registry $(IMAGE_NAME)

View File

@@ -26,7 +26,10 @@ RUN make DESTDIR="/root/dist" install
FROM rustlang/rust:nightly-alpine3.17
ENV LANG=en_US.UTF-8
RUN apk add --no-cache musl-dev ncurses gnutls
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"]

View File

@@ -25,11 +25,12 @@ 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)

1
elisp_snippets/README.md Normal file
View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -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.

View File

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

View File

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

View File

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

View File

@@ -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

View File

@@ -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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -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

View File

@@ -0,0 +1,22 @@
# Extra open
[cite/a/b-_/foo:unbalancedglobal[prefix;keyprefix @foo keysuffix;globalsuffix]
[cite/a/b-_/foo:globalprefix;unbalancedkey[prefix @foo keysuffix;globalsuffix]
[cite/a/b-_/foo:globalprefix;keyprefix @foo unbalancedkey[suffix;globalsuffix]
[cite/a/b-_/foo:globalprefix;keyprefix @foo keysuffix;unbalancedglobal[suffix]
# Extra close
[cite/a/b-_/foo:unbalancedglobal]prefix;keyprefix @foo keysuffix;globalsuffix]
[cite/a/b-_/foo:globalprefix;unbalancedkey]prefix @foo keysuffix;globalsuffix]
[cite/a/b-_/foo:globalprefix;keyprefix @foo unbalancedkey]suffix;globalsuffix]
[cite/a/b-_/foo:globalprefix;keyprefix @foo keysuffix;unbalancedglobal]suffix]
# balanced:
[cite/a/b-_/foo:gl[obalpref]ix;ke[ypref]ix @foo ke[ysuff]ix;gl[obalsuff]ix]

View File

@@ -0,0 +1,2 @@
[fn:2:This footnote [ has balanced ] brackets inside it]
[fn::This footnote does not have balanced [ brackets inside it]

View File

@@ -0,0 +1,6 @@
$foo
bar
baz
lorem
ipsum
dolar$

View File

@@ -0,0 +1,52 @@
non-link text
eww://
rmail://
mhe://
irc://
info://
gnus://
docview://
bibtex://
bbdb://
w3m://
doi://
file+sys://
file+emacs://
shell://
news://
mailto://
https://
http://
ftp://
help://
file://
elisp://
randomfakeprotocl://
non-link text
non-link text
eww:
rmail:
mhe:
irc:
info:
gnus:
docview:
bibtex:
bbdb:
w3m:
doi:
file+sys:
file+emacs:
shell:
news:
mailto:
https:
http:
ftp:
help:
file:
elisp:
randomfakeprotocl:
non-link text

View File

@@ -0,0 +1,3 @@
mailto:foo@bar.baz.
mailto:foo@bar.baz....

View File

@@ -0,0 +1,17 @@
foo *bar
baz* lorem
text *markup
can
span* more
than *three
lines.
foo
bar* baz
foo *bar \\
baz \\
lorem \\
ipsum \\
dolar* cat

View File

@@ -0,0 +1 @@
foo ==>bar=.

View File

@@ -0,0 +1,9 @@
* Foo
* Bar
* Baz

View File

@@ -0,0 +1 @@
🧡💛💚💙💜

View File

@@ -8,11 +8,22 @@ DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
cd "$DIR/../"
cargo build --profile "$PROFILE" --no-default-features
perf record --freq=2000 --call-graph dwarf --output=perf.data target/${PROFILE}/compare
# Convert to a format firefox will read
# flags to consider --show-info
perf script -F +pid --input perf.data > perf.firefox
function main {
local additional_flags=()
if [ "$PROFILE" = "dev" ] || [ "$PROFILE" = "debug" ]; then
PROFILE="debug"
else
additional_flags+=(--profile "$PROFILE")
fi
cargo build --no-default-features "${additional_flags[@]}"
perf record --freq=2000 --call-graph dwarf --output=perf.data target/${PROFILE}/compare
echo "You probably want to go to https://profiler.firefox.com/"
echo "Either that or run hotspot"
# Convert to a format firefox will read
# flags to consider --show-info
perf script -F +pid --input perf.data > perf.firefox
echo "You probably want to go to https://profiler.firefox.com/"
echo "Either that or run hotspot"
}
main "${@}"

View File

@@ -7,6 +7,8 @@ DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
: ${SHELL:="NO"} # or YES to launch a shell instead of running the test
: ${TRACE:="NO"} # or YES to send traces to jaeger
: ${BACKTRACE:="NO"} # or YES to print a rust backtrace when panicking
: ${NO_COLOR:=""} # Set to anything to disable color output
cd "$DIR/../"
REALPATH=$(command -v uu-realpath || command -v realpath)
@@ -24,23 +26,32 @@ function build_container {
function launch_container {
local additional_flags=()
local additional_args=()
local features=(compare)
if [ "$SHELL" != "YES" ]; then
additional_args+=(cargo run)
else
additional_flags+=(-t)
if [ "$NO_COLOR" != "" ]; then
additional_flags+=(--env "NO_COLOR=$NO_COLOR")
fi
if [ "$TRACE" = "YES" ]; then
# We use the host network so it can talk to jaeger hosted at 127.0.0.1
additional_flags+=(--network=host --env RUST_LOG=debug)
features+=(tracing)
fi
if [ "$SHELL" != "YES" ]; then
local features_joined=$(IFS=","; echo "${features[*]}")
additional_args+=(cargo run --no-default-features --features "$features_joined")
additional_flags+=(--read-only)
else
additional_args+=(/bin/sh)
additional_flags+=(-t)
fi
if [ "$BACKTRACE" = "YES" ]; then
additional_flags+=(--env RUST_BACKTRACE=full)
fi
docker run "${additional_flags[@]}" --init --rm -i -v "$($REALPATH ./):/source:ro" --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target -w /source organic-test "${additional_args[@]}"
docker run "${additional_flags[@]}" --init --rm -i --mount type=tmpfs,destination=/tmp -v "$($REALPATH ./):/source:ro" --mount source=cargo-cache,target=/usr/local/cargo/registry --mount source=rust-cache,target=/target --env CARGO_TARGET_DIR=/target -w /source --entrypoint "" organic-test "${additional_args[@]}"
}
main "${@}"

View File

@@ -4,6 +4,8 @@ set -euo pipefail
IFS=$'\n\t'
DIR="$( 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)
@@ -31,7 +33,7 @@ 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
@@ -40,17 +42,21 @@ function get_test_names {
function launch_container {
local test="$1"
local additional_args=()
local additional_flags=()
if [ "$NO_COLOR" != "" ]; then
additional_flags+=(--env "NO_COLOR=$NO_COLOR")
fi
local init_script=$(cat <<EOF
set -euo pipefail
IFS=\$'\n\t'
cargo test --no-fail-fast --lib --test test_loader "$test" -- --show-output
cargo test --no-default-features --features compare --no-fail-fast --lib --test test_loader "$test" -- --show-output
EOF
)
docker run --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 organic-test sh -c "$init_script"
docker run "${additional_flags[@]}" --init --rm --read-only --mount type=tmpfs,destination=/tmp -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"
}

View File

@@ -12,7 +12,7 @@ function main {
local test
while read test; do
cargo test --no-fail-fast --test test_loader "$test" -- --show-output
cargo test --no-default-features --features compare --no-fail-fast --test test_loader "$test" -- --show-output
done<<<"$test_names"
}
@@ -25,7 +25,7 @@ function get_test_names {
local test_file_full_path=$($REALPATH "$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

23
scripts/time_parse.bash Executable file
View File

@@ -0,0 +1,23 @@
#!/usr/bin/env bash
#
# Time running a single parse without invoking a compare with emacs.
set -euo pipefail
IFS=$'\n\t'
DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
: ${PROFILE:="release-lto"}
cd "$DIR/../"
function main {
local additional_flags=()
if [ "$PROFILE" = "dev" ] || [ "$PROFILE" = "debug" ]; then
PROFILE="debug"
else
additional_flags+=(--profile "$PROFILE")
fi
cargo build --no-default-features "${additional_flags[@]}"
time ./target/${PROFILE}/compare
}
main "${@}"

File diff suppressed because it is too large Load Diff

View File

@@ -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;
@@ -47,13 +47,14 @@ pub fn assert_bounds<'s, S: Source<'s>>(
standard_properties
.begin
.ok_or("Token should have a begin.")?,
standard_properties
.end
.ok_or("Token should have a begin.")?,
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 ({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(())
@@ -139,3 +140,23 @@ fn maybe_token_to_usize(
.flatten() // Outer option is whether or not the param exists, inner option is whether or not it is nil
.map_or(Ok(None), |r| r.map(Some))?)
}
pub fn get_property<'s, 'x>(
emacs: &'s Token<'s>,
key: &'x str,
) -> Result<Option<&'s Token<'s>>, Box<dyn std::error::Error>> {
let children = emacs.as_list()?;
let attributes_child = children
.iter()
.nth(1)
.ok_or("Should have an attributes child.")?;
let attributes_map = attributes_child.as_map()?;
let prop = attributes_map
.get(key)
.ok_or(format!("Missing {} attribute.", key))?;
match prop.as_atom() {
Ok("nil") => return Ok(None),
_ => {}
};
Ok(Some(*prop))
}

View File

@@ -55,20 +55,21 @@ fn read_stdin_to_string() -> Result<String, Box<dyn std::error::Error>> {
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.as_ref()).map_err(|e| e.to_string())?;
let org_sexp = emacs_parse_org_document(org_contents.as_ref())?;
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.as_ref());
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()?;
diff_result.print(org_contents)?;
if diff_result.is_bad() {
Err("Diff results do not match.")?;
@@ -85,7 +86,7 @@ fn run_compare<P: AsRef<str>>(org_contents: P) -> Result<(), Box<dyn std::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())?;
let (_remaining, rust_parsed) = document(org_contents.as_ref()).map_err(|e| e.to_string())?;
println!("{:#?}", rust_parsed);
Ok(())
}

View File

@@ -5,6 +5,7 @@ use nom::combinator::recognize;
use nom::multi::many_till;
use super::org_source::OrgSource;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
use crate::error::Res;
use crate::parser::exiting::ExitClass;
@@ -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,

View File

@@ -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;
@@ -11,17 +10,18 @@ use nom::multi::many_till;
use nom::multi::separated_list1;
use nom::sequence::tuple;
use super::citation_reference::must_balance_bracket;
use super::org_source::BracketDepth;
use super::org_source::OrgSource;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
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::citation_reference::get_bracket_depth;
use crate::parser::exiting::ExitClass;
use crate::parser::object::Citation;
use crate::parser::object_parser::standard_set_object;
use crate::parser::parser_context::CitationBracket;
use crate::parser::parser_context::ContextElement;
use crate::parser::parser_context::ExitMatcherNode;
use crate::parser::parser_with_context::parser_with_context;
@@ -38,15 +38,18 @@ pub fn citation<'r, 's>(
let (remaining, _) = tag_no_case("[cite")(input)?;
let (remaining, _) = opt(citestyle)(remaining)?;
let (remaining, _) = tag(":")(remaining)?;
let (remaining, _prefix) = opt(parser_with_context!(global_prefix)(context))(remaining)?;
let (remaining, _prefix) =
must_balance_bracket(opt(parser_with_context!(global_prefix)(context)))(remaining)?;
let (remaining, _references) =
separated_list1(tag(";"), parser_with_context!(citation_reference)(context))(remaining)?;
let (remaining, _suffix) = opt(tuple((
let (remaining, _suffix) = must_balance_bracket(opt(tuple((
tag(";"),
parser_with_context!(global_suffix)(context),
)))(remaining)?;
))))(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,
@@ -83,15 +86,11 @@ fn global_prefix<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Vec<Object<'s>>> {
// TODO: I could insert CitationBracket entries in the context after each matched object to reduce the scanning done for counting brackets which should be more efficient.
let parser_context = context
.with_additional_node(ContextElement::CitationBracket(CitationBracket {
position: input,
depth: 0,
}))
.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
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: &global_prefix_end,
exit_matcher: &exit_with_depth,
}));
let (remaining, (children, _exit_contents)) = verify(
many_till(
@@ -104,28 +103,24 @@ 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)
}
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn global_prefix_end<'r, 's>(
fn _global_prefix_end<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
starting_bracket_depth: BracketDepth,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let context_depth = get_bracket_depth(context)
.expect("This function should only be called from inside a citation.");
let text_since_context_entry = get_consumed(context_depth.position, input);
let mut current_depth = context_depth.depth;
for c in Into::<&str>::into(text_since_context_entry).chars() {
match c {
'[' => {
current_depth += 1;
}
']' if current_depth == 0 => {
panic!("Exceeded citation global prefix bracket depth.")
}
']' if current_depth > 0 => {
current_depth -= 1;
}
_ => {}
}
let current_depth = input.get_bracket_depth() - starting_bracket_depth;
if current_depth < 0 {
// This shouldn't be possible because if depth is 0 then a closing bracket should end the citation.
unreachable!("Exceeded citation global prefix bracket depth.")
}
if current_depth == 0 {
let close_bracket = tag::<&str, OrgSource<'_>, CustomError<OrgSource<'_>>>("]")(input);
@@ -144,15 +139,11 @@ fn global_suffix<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Vec<Object<'s>>> {
// TODO: I could insert CitationBracket entries in the context after each matched object to reduce the scanning done for counting brackets which should be more efficient.
let parser_context = context
.with_additional_node(ContextElement::CitationBracket(CitationBracket {
position: input,
depth: 0,
}))
.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
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: &global_suffix_end,
exit_matcher: &exit_with_depth,
}));
let (remaining, (children, _exit_contents)) = verify(
many_till(
@@ -164,28 +155,24 @@ 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)
}
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn global_suffix_end<'r, 's>(
fn _global_suffix_end<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
starting_bracket_depth: BracketDepth,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let context_depth = get_bracket_depth(context)
.expect("This function should only be called from inside a citation.");
let text_since_context_entry = get_consumed(context_depth.position, input);
let mut current_depth = context_depth.depth;
for c in Into::<&str>::into(text_since_context_entry).chars() {
match c {
'[' => {
current_depth += 1;
}
']' if current_depth == 0 => {
panic!("Exceeded citation global suffix bracket depth.")
}
']' if current_depth > 0 => {
current_depth -= 1;
}
_ => {}
}
let current_depth = input.get_bracket_depth() - starting_bracket_depth;
if current_depth < 0 {
// This shouldn't be possible because if depth is 0 then a closing bracket should end the citation.
unreachable!("Exceeded citation global suffix bracket depth.")
}
if current_depth == 0 {
let close_bracket = tag::<&str, OrgSource<'_>, CustomError<OrgSource<'_>>>("]")(input);

View File

@@ -10,14 +10,15 @@ use nom::multi::many_till;
use nom::sequence::preceded;
use nom::sequence::tuple;
use super::org_source::BracketDepth;
use super::org_source::OrgSource;
use super::Context;
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::CitationBracket;
use crate::parser::parser_context::ContextElement;
use crate::parser::parser_context::ExitMatcherNode;
use crate::parser::parser_with_context::parser_with_context;
@@ -31,9 +32,11 @@ pub fn citation_reference<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, CitationReference<'s>> {
let (remaining, _prefix) = opt(parser_with_context!(key_prefix)(context))(input)?;
let (remaining, _prefix) =
must_balance_bracket(opt(parser_with_context!(key_prefix)(context)))(input)?;
let (remaining, _key) = parser_with_context!(citation_reference_key)(context)(remaining)?;
let (remaining, _suffix) = opt(parser_with_context!(key_suffix)(context))(remaining)?;
let (remaining, _suffix) =
must_balance_bracket(opt(parser_with_context!(key_suffix)(context)))(remaining)?;
let source = get_consumed(input, remaining);
Ok((
@@ -69,15 +72,11 @@ fn key_prefix<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Vec<Object<'s>>> {
// TODO: I could insert CitationBracket entries in the context after each matched object to reduce the scanning done for counting brackets which should be more efficient.
let parser_context = context
.with_additional_node(ContextElement::CitationBracket(CitationBracket {
position: input,
depth: 0,
}))
.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
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: &key_prefix_end,
exit_matcher: &exit_with_depth,
}));
let (remaining, (children, _exit_contents)) = verify(
many_till(
@@ -94,15 +93,11 @@ fn key_suffix<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Vec<Object<'s>>> {
// TODO: I could insert CitationBracket entries in the context after each matched object to reduce the scanning done for counting brackets which should be more efficient.
let parser_context = context
.with_additional_node(ContextElement::CitationBracket(CitationBracket {
position: input,
depth: 0,
}))
.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
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: &key_suffix_end,
exit_matcher: &exit_with_depth,
}));
let (remaining, (children, _exit_contents)) = verify(
many_till(
@@ -114,39 +109,24 @@ fn key_suffix<'r, 's>(
Ok((remaining, children))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn get_bracket_depth<'r, 's>(context: Context<'r, 's>) -> Option<&'r CitationBracket<'s>> {
for node in context.iter() {
match node.get_data() {
ContextElement::CitationBracket(depth) => return Some(depth),
_ => {}
}
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)
}
None
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn key_prefix_end<'r, 's>(
fn _key_prefix_end<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
starting_bracket_depth: BracketDepth,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let context_depth = get_bracket_depth(context)
.expect("This function should only be called from inside a citation reference.");
let text_since_context_entry = get_consumed(context_depth.position, input);
let mut current_depth = context_depth.depth;
for c in Into::<&str>::into(text_since_context_entry).chars() {
match c {
'[' => {
current_depth += 1;
}
']' if current_depth == 0 => {
panic!("Exceeded citation reference key prefix bracket depth.")
}
']' if current_depth > 0 => {
current_depth -= 1;
}
_ => {}
}
let current_depth = input.get_bracket_depth() - starting_bracket_depth;
if current_depth < 0 {
// This shouldn't be possible because if depth is 0 then a closing bracket should end the citation.
unreachable!("Exceeded citation key prefix bracket depth.")
}
if current_depth == 0 {
let close_bracket = tag::<&str, OrgSource<'_>, CustomError<OrgSource<'_>>>("]")(input);
@@ -160,28 +140,24 @@ 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)
}
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn key_suffix_end<'r, 's>(
context: Context<'r, 's>,
fn _key_suffix_end<'r, 's>(
_context: Context<'r, 's>,
input: OrgSource<'s>,
starting_bracket_depth: BracketDepth,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let context_depth = get_bracket_depth(context)
.expect("This function should only be called from inside a citation reference.");
let text_since_context_entry = get_consumed(context_depth.position, input);
let mut current_depth = context_depth.depth;
for c in Into::<&str>::into(text_since_context_entry).chars() {
match c {
'[' => {
current_depth += 1;
}
']' if current_depth == 0 => {
panic!("Exceeded citation reference key prefix bracket depth.")
}
']' if current_depth > 0 => {
current_depth -= 1;
}
_ => {}
}
let current_depth = input.get_bracket_depth() - starting_bracket_depth;
if current_depth < 0 {
// This shouldn't be possible because if depth is 0 then a closing bracket should end the citation.
unreachable!("Exceeded citation key suffix bracket depth.")
}
if current_depth == 0 {
let close_bracket = tag::<&str, OrgSource<'_>, CustomError<OrgSource<'_>>>("]")(input);
@@ -191,3 +167,21 @@ fn key_suffix_end<'r, 's>(
}
tag(";")(input)
}
pub fn must_balance_bracket<'s, F, O>(
mut inner: F,
) -> impl FnMut(OrgSource<'s>) -> Res<OrgSource<'s>, O>
where
F: FnMut(OrgSource<'s>) -> Res<OrgSource<'s>, O>,
{
move |input: OrgSource<'_>| {
let pre_bracket_depth = input.get_bracket_depth();
let (remaining, output) = inner(input)?;
if remaining.get_bracket_depth() - pre_bracket_depth != 0 {
return Err(nom::Err::Error(CustomError::MyError(MyError(
"UnbalancedBrackets".into(),
))));
}
Ok((remaining, output))
}
}

View File

@@ -1,9 +1,12 @@
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::combinator::eof;
use nom::combinator::opt;
use nom::combinator::recognize;
use nom::multi::many_till;
use nom::sequence::tuple;
use super::org_source::OrgSource;
@@ -24,6 +27,11 @@ pub fn diary_sexp<'r, 's>(
let (remaining, _clock) = tag("%%")(remaining)?;
let (remaining, _gap_whitespace) = space0(remaining)?;
let (remaining, _sexp) = recognize(sexp)(remaining)?;
let (remaining, _trailing_comment) = opt(tuple((
space0,
tag(";"),
many_till(anychar, alt((line_ending, eof))),
)))(remaining)?;
let (remaining, _trailing_whitespace) =
recognize(tuple((space0, alt((line_ending, eof)))))(remaining)?;

View File

@@ -1,6 +1,8 @@
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;
@@ -12,6 +14,7 @@ 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;
@@ -50,7 +53,10 @@ pub struct Document<'s> {
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>>,
}
@@ -133,7 +139,7 @@ fn _document<'r, 's>(
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Document<'s>> {
let zeroth_section_matcher = parser_with_context!(zeroth_section)(context);
let heading_matcher = parser_with_context!(heading)(context);
let heading_matcher = parser_with_context!(heading(0))(context);
let (remaining, _blank_lines) = many0(blank_line)(input)?;
let (remaining, zeroth_section) = opt(zeroth_section_matcher)(remaining)?;
let (remaining, children) = many0(heading_matcher)(remaining)?;
@@ -254,69 +260,149 @@ fn section<'r, 's>(
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn section_end<'r, 's>(
context: Context<'r, 's>,
_context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let headline_matcher = parser_with_context!(headline)(context);
recognize(headline_matcher)(input)
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>(
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, title)) = headline(context, 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)(context);
let (remaining, children) = many0(alt((
map(
verify(heading_matcher, |h| h.stars > star_count),
DocumentElement::Heading,
),
map(section_matcher, DocumentElement::Section),
)))(remaining)?;
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 headline<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, (usize, OrgSource<'s>, Vec<Object<'s>>)> {
let parser_context =
context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
class: ExitClass::Document,
exit_matcher: &headline_end,
}));
let standard_set_object_matcher = parser_with_context!(standard_set_object)(&parser_context);
let (remaining, (_sol, star_count, ws, title, _line_ending)) = tuple((
start_of_line,
many1_count(tag("*")),
space1,
many1(standard_set_object_matcher),
alt((line_ending, eof)),
))(input)?;
Ok((remaining, (star_count, ws, title)))
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_end<'r, 's>(
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>> {
line_ending(input)
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> {

View File

@@ -12,6 +12,7 @@ use super::fixed_width_area::fixed_width_area;
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::keyword;
use super::latex_environment::latex_environment;
use super::lesser_block::comment_block;
@@ -62,10 +63,12 @@ fn _element<'r, 's>(
let fixed_width_area_matcher = parser_with_context!(fixed_width_area)(context);
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 paragraph_matcher = parser_with_context!(paragraph)(context);
let latex_environment_matcher = parser_with_context!(latex_environment)(context);
let (remaining, mut affiliated_keywords) = many0(keyword_matcher)(input)?;
// TODO: Affiliated keywords cannot be on comments, clocks, headings, inlinetasks, items, node properties, planning, property drawers, sections, and table rows
let (remaining, mut affiliated_keywords) = many0(affiliated_keyword_matcher)(input)?;
let (remaining, mut element) = match alt((
map(plain_list_matcher, Element::PlainList),
map(greater_block_matcher, Element::GreaterBlock),
@@ -84,6 +87,7 @@ fn _element<'r, 's>(
map(fixed_width_area_matcher, Element::FixedWidthArea),
map(horizontal_rule_matcher, Element::HorizontalRule),
map(latex_environment_matcher, Element::LatexEnvironment),
map(keyword_matcher, Element::Keyword),
))(remaining)
{
the_ok @ Ok(_) => the_ok,
@@ -93,12 +97,12 @@ fn _element<'r, 's>(
the_ok @ Ok(_) => the_ok,
Err(_) => {
affiliated_keywords.clear();
map(keyword_matcher, Element::Keyword)(input)
map(affiliated_keyword_matcher, Element::Keyword)(input)
}
}
} else {
affiliated_keywords.clear();
map(keyword_matcher, Element::Keyword)(input)
map(affiliated_keyword_matcher, Element::Keyword)(input)
}
}
}?;
@@ -124,7 +128,7 @@ fn _detect_element<'r, 's>(
input: OrgSource<'s>,
can_be_paragraph: bool,
) -> Res<OrgSource<'s>, ()> {
if detect_plain_list(context, input).is_ok() {
if detect_plain_list(input).is_ok() {
return Ok((input, ()));
}
if _element(context, input, can_be_paragraph).is_ok() {

View File

@@ -2,18 +2,436 @@ use nom::branch::alt;
use nom::bytes::complete::tag;
use nom::bytes::complete::tag_no_case;
use nom::character::complete::satisfy;
use nom::character::complete::space0;
use nom::combinator::eof;
use nom::combinator::peek;
use nom::combinator::recognize;
use super::org_source::OrgSource;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
use crate::error::CustomError;
use crate::error::MyError;
use crate::error::Res;
use crate::parser::object::Entity;
use crate::parser::parser_with_context::parser_with_context;
use crate::parser::util::get_consumed;
// TODO: Make this a user-provided variable corresponding to elisp's org-entities
const ORG_ENTITIES: [&'static str; 413] = [
"Agrave",
"agrave",
"Aacute",
"aacute",
"Acirc",
"acirc",
"Amacr",
"amacr",
"Atilde",
"atilde",
"Auml",
"auml",
"Aring",
"AA",
"aring",
"AElig",
"aelig",
"Ccedil",
"ccedil",
"Egrave",
"egrave",
"Eacute",
"eacute",
"Ecirc",
"ecirc",
"Euml",
"euml",
"Igrave",
"igrave",
"Iacute",
"iacute",
"Idot",
"inodot",
"Icirc",
"icirc",
"Iuml",
"iuml",
"Ntilde",
"ntilde",
"Ograve",
"ograve",
"Oacute",
"oacute",
"Ocirc",
"ocirc",
"Otilde",
"otilde",
"Ouml",
"ouml",
"Oslash",
"oslash",
"OElig",
"oelig",
"Scaron",
"scaron",
"szlig",
"Ugrave",
"ugrave",
"Uacute",
"uacute",
"Ucirc",
"ucirc",
"Uuml",
"uuml",
"Yacute",
"yacute",
"Yuml",
"yuml",
"fnof",
"real",
"image",
"weierp",
"ell",
"imath",
"jmath",
"Alpha",
"alpha",
"Beta",
"beta",
"Gamma",
"gamma",
"Delta",
"delta",
"Epsilon",
"epsilon",
"varepsilon",
"Zeta",
"zeta",
"Eta",
"eta",
"Theta",
"theta",
"thetasym",
"vartheta",
"Iota",
"iota",
"Kappa",
"kappa",
"Lambda",
"lambda",
"Mu",
"mu",
"nu",
"Nu",
"Xi",
"xi",
"Omicron",
"omicron",
"Pi",
"pi",
"Rho",
"rho",
"Sigma",
"sigma",
"sigmaf",
"varsigma",
"Tau",
"Upsilon",
"upsih",
"upsilon",
"Phi",
"phi",
"varphi",
"Chi",
"chi",
"acutex",
"Psi",
"psi",
"tau",
"Omega",
"omega",
"piv",
"varpi",
"partial",
"alefsym",
"aleph",
"gimel",
"beth",
"dalet",
"ETH",
"eth",
"THORN",
"thorn",
"dots",
"cdots",
"hellip",
"middot",
"iexcl",
"iquest",
"shy",
"ndash",
"mdash",
"quot",
"acute",
"ldquo",
"rdquo",
"bdquo",
"lsquo",
"rsquo",
"sbquo",
"laquo",
"raquo",
"lsaquo",
"rsaquo",
"circ",
"vert",
"vbar",
"brvbar",
"S",
"sect",
"amp",
"lt",
"gt",
"tilde",
"slash",
"plus",
"under",
"equal",
"asciicirc",
"dagger",
"dag",
"Dagger",
"ddag",
"nbsp",
"ensp",
"emsp",
"thinsp",
"curren",
"cent",
"pound",
"yen",
"euro",
"EUR",
"dollar",
"USD",
"copy",
"reg",
"trade",
"minus",
"pm",
"plusmn",
"times",
"frasl",
"colon",
"div",
"frac12",
"frac14",
"frac34",
"permil",
"sup1",
"sup2",
"sup3",
"radic",
"sum",
"prod",
"micro",
"macr",
"deg",
"prime",
"Prime",
"infin",
"infty",
"prop",
"propto",
"not",
"neg",
"land",
"wedge",
"lor",
"vee",
"cap",
"cup",
"smile",
"frown",
"int",
"therefore",
"there4",
"because",
"sim",
"cong",
"simeq",
"asymp",
"approx",
"ne",
"neq",
"equiv",
"triangleq",
"le",
"leq",
"ge",
"geq",
"lessgtr",
"lesseqgtr",
"ll",
"Ll",
"lll",
"gg",
"Gg",
"ggg",
"prec",
"preceq",
"preccurlyeq",
"succ",
"succeq",
"succcurlyeq",
"sub",
"subset",
"sup",
"supset",
"nsub",
"sube",
"nsup",
"supe",
"setminus",
"forall",
"exist",
"exists",
"nexist",
"nexists",
"empty",
"emptyset",
"isin",
"in",
"notin",
"ni",
"nabla",
"ang",
"angle",
"perp",
"parallel",
"sdot",
"cdot",
"lceil",
"rceil",
"lfloor",
"rfloor",
"lang",
"rang",
"langle",
"rangle",
"hbar",
"mho",
"larr",
"leftarrow",
"gets",
"lArr",
"Leftarrow",
"uarr",
"uparrow",
"uArr",
"Uparrow",
"rarr",
"to",
"rightarrow",
"rArr",
"Rightarrow",
"darr",
"downarrow",
"dArr",
"Downarrow",
"harr",
"leftrightarrow",
"hArr",
"Leftrightarrow",
"crarr",
"hookleftarrow",
"arccos",
"arcsin",
"arctan",
"arg",
"cos",
"cosh",
"cot",
"coth",
"csc",
"deg",
"det",
"dim",
"exp",
"gcd",
"hom",
"inf",
"ker",
"lg",
"lim",
"liminf",
"limsup",
"ln",
"log",
"max",
"min",
"Pr",
"sec",
"sin",
"sinh",
"sup",
"tan",
"tanh",
"bull",
"bullet",
"star",
"lowast",
"ast",
"odot",
"oplus",
"otimes",
"check",
"checkmark",
"para",
"ordf",
"ordm",
"cedil",
"oline",
"uml",
"zwnj",
"zwj",
"lrm",
"rlm",
"smiley",
"blacksmile",
"sad",
"frowny",
"clubs",
"clubsuit",
"spades",
"spadesuit",
"hearts",
"heartsuit",
"diams",
"diamondsuit",
"diamond",
"Diamond",
"loz",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
"_ ",
];
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn entity<'r, 's>(
context: Context<'r, 's>,
@@ -21,11 +439,9 @@ pub fn entity<'r, 's>(
) -> Res<OrgSource<'s>, Entity<'s>> {
let (remaining, _) = tag("\\")(input)?;
let (remaining, entity_name) = name(context, remaining)?;
let (remaining, _) = alt((
tag("{}"),
peek(recognize(parser_with_context!(entity_end)(context))),
))(remaining)?;
let (remaining, _) = space0(remaining)?;
let (remaining, _) = alt((tag("{}"), peek(recognize(entity_end))))(remaining)?;
let (remaining, _trailing_whitespace) =
maybe_consume_object_trailing_whitespace_if_not_exiting(context, remaining)?;
let source = get_consumed(input, remaining);
Ok((
@@ -43,14 +459,23 @@ fn name<'r, 's>(
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
// TODO: This should be defined by org-entities and optionally org-entities-user
for entity in ORG_ENTITIES {
let result = tag_no_case::<_, _, CustomError<_>>(entity)(input);
match result {
Ok((remaining, ent)) => {
return Ok((remaining, ent));
}
Err(_) => {}
}
}
// TODO: Add the rest of the entities, this is a very incomplete list
let (remaining, proto) = alt((alt((tag_no_case("delta"), tag_no_case("pi"))),))(input)?;
Ok((remaining, proto))
Err(nom::Err::Error(CustomError::MyError(MyError(
"NoEntity".into(),
))))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn entity_end<'r, 's>(_context: Context<'r, 's>, input: OrgSource<'s>) -> Res<OrgSource<'s>, ()> {
fn entity_end<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, ()> {
let (remaining, _) = alt((eof, recognize(satisfy(|c| !c.is_alphabetic()))))(input)?;
Ok((remaining, ()))

View File

@@ -8,6 +8,7 @@ use nom::multi::many_till;
use nom::sequence::tuple;
use super::org_source::OrgSource;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
use crate::error::Res;
use crate::parser::exiting::ExitClass;
@@ -35,6 +36,8 @@ pub fn export_snippet<'r, 's>(
parser_with_context!(contents)(&parser_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,

View File

@@ -80,21 +80,10 @@ fn footnote_definition_end<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let allow_nesting_context =
context.with_additional_node(ContextElement::Context("allow nesting footnotes"));
let footnote_definition_matcher = parser_with_context!(footnote_definition)(
if immediate_in_section(context, "footnote definition") {
&allow_nesting_context
} else {
context
},
);
let maybe_consume_trailing_whitespace_matcher =
parser_with_context!(maybe_consume_trailing_whitespace)(context);
let (remaining, source) = alt((
recognize(tuple((
maybe_consume_trailing_whitespace_matcher,
footnote_definition_matcher,
parser_with_context!(maybe_consume_trailing_whitespace)(context),
detect_footnote_definition,
))),
recognize(tuple((
start_of_line,
@@ -107,6 +96,12 @@ fn footnote_definition_end<'r, 's>(
Ok((remaining, source))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn detect_footnote_definition<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, ()> {
tuple((start_of_line, tag_no_case("[fn:"), label, tag("]")))(input)?;
Ok((input, ()))
}
#[cfg(test)]
mod tests {
use super::*;

View File

@@ -1,12 +1,13 @@
use nom::branch::alt;
use nom::bytes::complete::tag;
use nom::bytes::complete::tag_no_case;
use nom::character::complete::space0;
use nom::combinator::verify;
use nom::multi::many_till;
use super::org_source::BracketDepth;
use super::org_source::OrgSource;
use super::parser_context::ContextElement;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
use crate::error::CustomError;
use crate::error::MyError;
@@ -15,7 +16,6 @@ use crate::parser::exiting::ExitClass;
use crate::parser::footnote_definition::label;
use crate::parser::object_parser::standard_set_object;
use crate::parser::parser_context::ExitMatcherNode;
use crate::parser::parser_context::FootnoteReferenceDefinition;
use crate::parser::parser_with_context::parser_with_context;
use crate::parser::util::exit_matcher_parser;
use crate::parser::util::get_consumed;
@@ -39,18 +39,12 @@ fn anonymous_footnote<'r, 's>(
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, FootnoteReference<'s>> {
let (remaining, _) = tag_no_case("[fn::")(input)?;
let parser_context = context
.with_additional_node(ContextElement::FootnoteReferenceDefinition(
FootnoteReferenceDefinition {
position: remaining,
depth: 0,
},
))
.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
let exit_with_depth = footnote_definition_end(remaining.get_bracket_depth());
let parser_context =
context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
class: ExitClass::Beta,
exit_matcher: &footnote_definition_end,
exit_matcher: &exit_with_depth,
}));
// TODO: I could insert FootnoteReferenceDefinition entries in the context after each matched object to reduce the scanning done for counting brackets which should be more efficient.
let (remaining, (children, _exit_contents)) = verify(
many_till(
parser_with_context!(standard_set_object)(&parser_context),
@@ -60,7 +54,8 @@ fn anonymous_footnote<'r, 's>(
)(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,
@@ -80,18 +75,12 @@ fn inline_footnote<'r, 's>(
let (remaining, _) = tag_no_case("[fn:")(input)?;
let (remaining, label_contents) = label(remaining)?;
let (remaining, _) = tag(":")(remaining)?;
let parser_context = context
.with_additional_node(ContextElement::FootnoteReferenceDefinition(
FootnoteReferenceDefinition {
position: remaining,
depth: 0,
},
))
.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
let exit_with_depth = footnote_definition_end(remaining.get_bracket_depth());
let parser_context =
context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
class: ExitClass::Beta,
exit_matcher: &footnote_definition_end,
exit_matcher: &exit_with_depth,
}));
// TODO: I could insert FootnoteReferenceDefinition entries in the context after each matched object to reduce the scanning done for counting brackets which should be more efficient.
let (remaining, (children, _exit_contents)) = verify(
many_till(
parser_with_context!(standard_set_object)(&parser_context),
@@ -101,7 +90,8 @@ fn inline_footnote<'r, 's>(
)(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,
@@ -115,13 +105,14 @@ fn inline_footnote<'r, 's>(
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn footnote_reference_only<'r, 's>(
_context: Context<'r, 's>,
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, FootnoteReference<'s>> {
let (remaining, _) = tag_no_case("[fn:")(input)?;
let (remaining, label_contents) = label(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,
@@ -133,47 +124,30 @@ fn footnote_reference_only<'r, 's>(
))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn footnote_definition_end<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let context_depth = get_bracket_depth(context)
.expect("This function should only be called from inside a footnote definition.");
let text_since_context_entry = get_consumed(context_depth.position, input);
let mut current_depth = context_depth.depth;
for c in Into::<&str>::into(text_since_context_entry).chars() {
match c {
'[' => {
current_depth += 1;
}
']' if current_depth == 0 => {
panic!("Exceeded footnote reference definition bracket depth.")
}
']' if current_depth > 0 => {
current_depth -= 1;
}
_ => {}
}
fn footnote_definition_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<'_>| {
_footnote_definition_end(context, input, starting_bracket_depth)
}
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn _footnote_definition_end<'r, 's>(
_context: Context<'r, 's>,
input: OrgSource<'s>,
starting_bracket_depth: BracketDepth,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let current_depth = input.get_bracket_depth() - starting_bracket_depth;
if current_depth > 0 {
// Its impossible for the next character to end the footnote reference definition if we're any amount of brackets deep
return Err(nom::Err::Error(CustomError::MyError(MyError(
"NoFootnoteReferenceDefinitionEnd".into(),
))));
}
if current_depth < 0 {
// This shouldn't be possible because if depth is 0 then a closing bracket should end the footnote definition.
unreachable!("Exceeded footnote reference definition bracket depth.")
}
tag("]")(input)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn get_bracket_depth<'r, 's>(
context: Context<'r, 's>,
) -> Option<&'r FootnoteReferenceDefinition<'s>> {
for node in context.iter() {
match node.get_data() {
ContextElement::FootnoteReferenceDefinition(depth) => return Some(depth),
_ => {}
}
}
None
}

View File

@@ -12,6 +12,7 @@ use nom::multi::many_till;
use nom::sequence::tuple;
use super::org_source::OrgSource;
use super::util::in_section;
use super::Context;
use crate::error::CustomError;
use crate::error::MyError;
@@ -26,7 +27,6 @@ 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::parser::Paragraph;
@@ -49,24 +49,24 @@ pub fn greater_block<'r, 's>(
}),
))(remaining)?;
let context_name = match Into::<&str>::into(name).to_lowercase().as_str() {
"center" => "center block",
"quote" => "quote block",
_ => "greater block",
"center" => "center block".to_owned(),
"quote" => "quote block".to_owned(),
name @ _ => format!("special block {}", name),
};
if immediate_in_section(context, context_name) {
if in_section(context, context_name.as_str()) {
return Err(nom::Err::Error(CustomError::MyError(MyError(
"Cannot nest objects of the same element".into(),
))));
}
let exit_with_name = greater_block_end(name.into());
let (remaining, parameters) = opt(tuple((space1, parameters)))(remaining)?;
let (remaining, _nl) = line_ending(remaining)?;
let parser_context = context
.with_additional_node(ContextElement::ConsumeTrailingWhitespace(true))
.with_additional_node(ContextElement::Context(context_name))
.with_additional_node(ContextElement::GreaterBlock(name.into()))
.with_additional_node(ContextElement::Context(context_name.as_str()))
.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
class: ExitClass::Alpha,
exit_matcher: &greater_block_end,
exit_matcher: &exit_with_name,
}));
let parameters = match parameters {
Some((_ws, parameters)) => Some(parameters),
@@ -94,7 +94,7 @@ pub fn greater_block<'r, 's>(
(remaining, children)
}
};
let (remaining, _end) = greater_block_end(&parser_context, remaining)?;
let (remaining, _end) = exit_with_name(&parser_context, remaining)?;
// Not checking if parent exit matcher is causing exit because the greater_block_end matcher asserts we matched a full greater block
@@ -120,31 +120,27 @@ fn parameters<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
is_not("\r\n")(input)
}
fn greater_block_end<'x>(
name: &'x str,
) -> impl for<'r, 's> Fn(Context<'r, 's>, OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
// TODO: Can this be done without making an owned copy?
let name = name.to_owned();
move |context: Context, input: OrgSource<'_>| _greater_block_end(context, input, name.as_str())
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn greater_block_end<'r, 's>(
context: Context<'r, 's>,
fn _greater_block_end<'r, 's, 'x>(
_context: Context<'r, 's>,
input: OrgSource<'s>,
name: &'x str,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
start_of_line(input)?;
let current_name: &str = get_context_greater_block_name(context).ok_or(nom::Err::Error(
CustomError::MyError(MyError("Not inside a greater block".into())),
))?;
let (remaining, _leading_whitespace) = space0(input)?;
let (remaining, (_begin, _name, _ws)) = tuple((
tag_no_case("#+end_"),
tag_no_case(current_name),
tag_no_case(name),
alt((eof, line_ending)),
))(remaining)?;
let source = get_consumed(input, remaining);
Ok((remaining, source))
}
fn get_context_greater_block_name<'r, 's>(context: Context<'r, 's>) -> Option<&'s str> {
for thing in context.iter() {
match thing.get_data() {
ContextElement::GreaterBlock(name) => return Some(name),
_ => {}
};
}
None
}

View File

@@ -1,6 +1,7 @@
use super::element::Element;
use super::lesser_element::TableCell;
use super::source::Source;
use super::Object;
#[derive(Debug)]
pub struct PlainList<'s> {
@@ -13,6 +14,7 @@ pub struct PlainListItem<'s> {
pub source: &'s str,
pub indentation: usize,
pub bullet: &'s str,
pub tag: Vec<Object<'s>>,
pub children: Vec<Element<'s>>,
}

View File

@@ -4,17 +4,19 @@ use nom::bytes::complete::tag_no_case;
use nom::character::complete::anychar;
use nom::character::complete::line_ending;
use nom::character::complete::one_of;
use nom::character::complete::space0;
use nom::combinator::opt;
use nom::combinator::recognize;
use nom::combinator::verify;
use nom::multi::many_till;
use super::org_source::BracketDepth;
use super::org_source::OrgSource;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
use crate::error::CustomError;
use crate::error::MyError;
use crate::error::Res;
use crate::parser::exiting::ExitClass;
use crate::parser::parser_context::BabelHeaderBracket;
use crate::parser::parser_context::ContextElement;
use crate::parser::parser_context::ExitMatcherNode;
use crate::parser::parser_with_context::parser_with_context;
@@ -32,7 +34,8 @@ pub fn inline_babel_call<'r, 's>(
let (remaining, _header1) = opt(parser_with_context!(header)(context))(remaining)?;
let (remaining, _argument) = argument(context, remaining)?;
let (remaining, _header2) = opt(parser_with_context!(header)(context))(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,
@@ -74,14 +77,11 @@ fn header<'r, 's>(
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let (remaining, _) = tag("[")(input)?;
let parser_context = context
.with_additional_node(ContextElement::BabelHeaderBracket(BabelHeaderBracket {
position: remaining,
depth: 0,
}))
.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
let exit_with_depth = header_end(remaining.get_bracket_depth());
let parser_context =
context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
class: ExitClass::Gamma,
exit_matcher: &header_end,
exit_matcher: &exit_with_depth,
}));
let (remaining, name) = recognize(many_till(
@@ -92,28 +92,30 @@ fn header<'r, 's>(
Ok((remaining, name))
}
fn header_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<'_>| {
_header_end(context, input, starting_bracket_depth)
}
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn header_end<'r, 's>(
context: Context<'r, 's>,
fn _header_end<'r, 's>(
_context: Context<'r, 's>,
input: OrgSource<'s>,
starting_bracket_depth: BracketDepth,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let context_depth = get_bracket_depth(context)
.expect("This function should only be called from inside an inline babel call header.");
let text_since_context_entry = get_consumed(context_depth.position, input);
let mut current_depth = context_depth.depth;
for c in Into::<&str>::into(text_since_context_entry).chars() {
match c {
'(' => {
current_depth += 1;
}
')' if current_depth == 0 => {
panic!("Exceeded inline babel call header bracket depth.")
}
')' if current_depth > 0 => {
current_depth -= 1;
}
_ => {}
}
let current_depth = input.get_bracket_depth() - starting_bracket_depth;
if current_depth > 0 {
// Its impossible for the next character to end the header if we're any amount of bracket deep
return Err(nom::Err::Error(CustomError::MyError(MyError(
"NoHeaderEnd".into(),
))));
}
if current_depth < 0 {
// This shouldn't be possible because if depth is 0 then a closing bracket should end the header.
unreachable!("Exceeded header bracket depth.")
}
alt((tag("]"), line_ending))(input)
}
@@ -125,14 +127,11 @@ fn argument<'r, 's>(
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let (remaining, _) = tag("(")(input)?;
let parser_context = context
.with_additional_node(ContextElement::BabelHeaderBracket(BabelHeaderBracket {
position: remaining,
depth: 0,
}))
.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
let exit_with_depth = argument_end(remaining.get_parenthesis_depth());
let parser_context =
context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
class: ExitClass::Gamma,
exit_matcher: &argument_end,
exit_matcher: &exit_with_depth,
}));
let (remaining, name) = recognize(many_till(
@@ -143,39 +142,30 @@ fn argument<'r, 's>(
Ok((remaining, name))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn argument_end<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let context_depth = get_bracket_depth(context)
.expect("This function should only be called from inside an inline babel call argument.");
let text_since_context_entry = get_consumed(context_depth.position, input);
let mut current_depth = context_depth.depth;
for c in Into::<&str>::into(text_since_context_entry).chars() {
match c {
'[' => {
current_depth += 1;
}
']' if current_depth == 0 => {
panic!("Exceeded inline babel call argument bracket depth.")
}
']' if current_depth > 0 => {
current_depth -= 1;
}
_ => {}
}
fn argument_end(
starting_parenthesis_depth: BracketDepth,
) -> impl for<'r, 's> Fn(Context<'r, 's>, OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
move |context: Context, input: OrgSource<'_>| {
_argument_end(context, input, starting_parenthesis_depth)
}
alt((tag(")"), line_ending))(input)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn get_bracket_depth<'r, 's>(context: Context<'r, 's>) -> Option<&'r BabelHeaderBracket<'s>> {
for node in context.iter() {
match node.get_data() {
ContextElement::BabelHeaderBracket(depth) => return Some(depth),
_ => {}
}
fn _argument_end<'r, 's>(
_context: Context<'r, 's>,
input: OrgSource<'s>,
starting_parenthesis_depth: BracketDepth,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let current_depth = input.get_parenthesis_depth() - starting_parenthesis_depth;
if current_depth > 0 {
// Its impossible for the next character to end the argument if we're any amount of parenthesis deep
return Err(nom::Err::Error(CustomError::MyError(MyError(
"NoArgumentEnd".into(),
))));
}
None
if current_depth < 0 {
// This shouldn't be possible because if depth is 0 then a closing parenthesis should end the argument.
unreachable!("Exceeded argument parenthesis depth.")
}
alt((tag(")"), line_ending))(input)
}

View File

@@ -1,9 +1,9 @@
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::line_ending;
use nom::character::complete::one_of;
use nom::character::complete::space0;
use nom::combinator::opt;
use nom::combinator::recognize;
use nom::combinator::verify;
@@ -11,14 +11,16 @@ use nom::multi::many_till;
#[cfg(feature = "tracing")]
use tracing::span;
use super::org_source::BracketDepth;
use super::org_source::OrgSource;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
use crate::error::CustomError;
use crate::error::MyError;
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_context::InlineSourceBlockBracket;
use crate::parser::parser_with_context::parser_with_context;
use crate::parser::util::exit_matcher_parser;
use crate::parser::util::get_consumed;
@@ -33,7 +35,8 @@ pub fn inline_source_block<'r, 's>(
let (remaining, _) = lang(context, remaining)?;
let (remaining, _header1) = opt(parser_with_context!(header)(context))(remaining)?;
let (remaining, _body) = body(context, 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,
@@ -75,16 +78,11 @@ fn header<'r, 's>(
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let (remaining, _) = tag("[")(input)?;
let parser_context = context
.with_additional_node(ContextElement::InlineSourceBlockBracket(
InlineSourceBlockBracket {
position: remaining,
depth: 0,
},
))
.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
let exit_with_depth = header_end(remaining.get_bracket_depth());
let parser_context =
context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
class: ExitClass::Beta,
exit_matcher: &header_end,
exit_matcher: &exit_with_depth,
}));
let (remaining, header_contents) = recognize(many_till(
@@ -95,37 +93,32 @@ fn header<'r, 's>(
Ok((remaining, header_contents))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn header_end<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let context_depth = get_bracket_depth(context)
.expect("This function should only be called from inside an inline source block header.");
let text_since_context_entry = get_consumed(context_depth.position, input);
let mut current_depth = context_depth.depth;
for c in Into::<&str>::into(text_since_context_entry).chars() {
match c {
'[' => {
current_depth += 1;
}
']' if current_depth == 0 => {
panic!("Exceeded inline source block header bracket depth.")
}
']' if current_depth > 0 => {
current_depth -= 1;
}
_ => {}
}
}
if current_depth == 0 {
let close_bracket = tag::<&str, OrgSource<'_>, CustomError<OrgSource<'_>>>("]")(input);
if close_bracket.is_ok() {
return close_bracket;
}
fn header_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<'_>| {
_header_end(context, input, starting_bracket_depth)
}
}
line_ending(input)
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn _header_end<'r, 's>(
_context: Context<'r, 's>,
input: OrgSource<'s>,
starting_bracket_depth: BracketDepth,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let current_depth = input.get_bracket_depth() - starting_bracket_depth;
if current_depth > 0 {
// Its impossible for the next character to end the header if we're any amount of bracket deep
return Err(nom::Err::Error(CustomError::MyError(MyError(
"NoHeaderEnd".into(),
))));
}
if current_depth < 0 {
// This shouldn't be possible because if depth is 0 then a closing bracket should end the header.
unreachable!("Exceeded header bracket depth.")
}
alt((tag("]"), line_ending))(input)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
@@ -135,16 +128,11 @@ fn body<'r, 's>(
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let (remaining, _) = tag("{")(input)?;
let parser_context = context
.with_additional_node(ContextElement::InlineSourceBlockBracket(
InlineSourceBlockBracket {
position: remaining,
depth: 0,
},
))
.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
let exit_with_depth = body_end(remaining.get_brace_depth());
let parser_context =
context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
class: ExitClass::Beta,
exit_matcher: &body_end,
exit_matcher: &exit_with_depth,
}));
let (remaining, body_contents) = recognize(many_till(
@@ -165,60 +153,28 @@ fn body<'r, 's>(
Ok((remaining, body_contents))
}
fn body_end(
starting_brace_depth: BracketDepth,
) -> impl for<'r, 's> Fn(Context<'r, 's>, OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
move |context: Context, input: OrgSource<'_>| _body_end(context, input, starting_brace_depth)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn body_end<'r, 's>(
context: Context<'r, 's>,
fn _body_end<'r, 's>(
_context: Context<'r, 's>,
input: OrgSource<'s>,
starting_brace_depth: BracketDepth,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let context_depth = get_bracket_depth(context)
.expect("This function should only be called from inside an inline source block body.");
let text_since_context_entry = get_consumed(context_depth.position, input);
let mut current_depth = context_depth.depth;
for c in Into::<&str>::into(text_since_context_entry).chars() {
match c {
'{' => {
current_depth += 1;
}
'}' if current_depth == 0 => {
panic!("Exceeded inline source block body bracket depth.")
}
'}' if current_depth > 0 => {
current_depth -= 1;
}
_ => {}
}
let current_depth = input.get_brace_depth() - starting_brace_depth;
if current_depth > 0 {
// Its impossible for the next character to end the body if we're any amount of brace deep
return Err(nom::Err::Error(CustomError::MyError(MyError(
"NoBodyEnd".into(),
))));
}
{
#[cfg(feature = "tracing")]
let span = span!(
tracing::Level::DEBUG,
"inside end body",
remaining = Into::<&str>::into(input),
current_depth = current_depth
);
#[cfg(feature = "tracing")]
let _enter = span.enter();
if current_depth == 0 {
let close_bracket = tag::<&str, OrgSource<'_>, CustomError<OrgSource<'_>>>("}")(input);
if close_bracket.is_ok() {
return close_bracket;
}
}
if current_depth < 0 {
// This shouldn't be possible because if depth is 0 then a closing brace should end the body.
unreachable!("Exceeded body brace depth.")
}
line_ending(input)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn get_bracket_depth<'r, 's>(
context: Context<'r, 's>,
) -> Option<&'r InlineSourceBlockBracket<'s>> {
for node in context.iter() {
match node.get_data() {
ContextElement::InlineSourceBlockBracket(depth) => return Some(depth),
_ => {}
}
}
None
alt((tag("}"), line_ending))(input)
}

View File

@@ -2,6 +2,8 @@ use nom::branch::alt;
use nom::bytes::complete::is_not;
use nom::bytes::complete::tag;
use nom::bytes::complete::tag_no_case;
use nom::bytes::complete::take_while1;
use nom::character::complete::anychar;
use nom::character::complete::line_ending;
use nom::character::complete::space0;
use nom::character::complete::space1;
@@ -9,14 +11,24 @@ use nom::combinator::eof;
use nom::combinator::not;
use nom::combinator::peek;
use nom::combinator::recognize;
use nom::multi::many_till;
use nom::sequence::tuple;
use super::org_source::BracketDepth;
use super::org_source::OrgSource;
use super::Context;
use crate::error::CustomError;
use crate::error::MyError;
use crate::error::Res;
use crate::parser::util::start_of_line;
use crate::parser::Keyword;
const ORG_ELEMENT_AFFILIATED_KEYWORDS: [&'static str; 13] = [
"caption", "data", "header", "headers", "label", "name", "plot", "resname", "result",
"results", "source", "srcname", "tblname",
];
const ORG_ELEMENT_DUAL_KEYWORDS: [&'static str; 2] = ["caption", "results"];
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn keyword<'r, 's>(
_context: Context<'r, 's>,
@@ -41,3 +53,111 @@ pub fn keyword<'r, 's>(
},
))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn affiliated_keyword<'r, 's>(
_context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Keyword<'s>> {
start_of_line(input)?;
// TODO: When key is a member of org-element-parsed-keywords, value can contain the standard set objects, excluding footnote references.
let (remaining, rule) = recognize(tuple((
space0,
tag("#+"),
affiliated_key,
tag(":"),
alt((recognize(tuple((space1, is_not("\r\n")))), space0)),
alt((line_ending, eof)),
)))(input)?;
Ok((
remaining,
Keyword {
source: rule.into(),
},
))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn affiliated_key<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
alt((
recognize(tuple((dual_affiliated_key, tag("["), optval, tag("]")))),
plain_affiliated_key,
export_keyword,
))(input)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn plain_affiliated_key<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
for keyword in ORG_ELEMENT_AFFILIATED_KEYWORDS {
let result = tag_no_case::<_, _, CustomError<_>>(keyword)(input);
match result {
Ok((remaining, ent)) => {
return Ok((remaining, ent));
}
Err(_) => {}
}
}
Err(nom::Err::Error(CustomError::MyError(MyError(
"NoKeywordKey".into(),
))))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn dual_affiliated_key<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
for keyword in ORG_ELEMENT_DUAL_KEYWORDS {
let result = tag_no_case::<_, _, CustomError<_>>(keyword)(input);
match result {
Ok((remaining, ent)) => {
return Ok((remaining, ent));
}
Err(_) => {}
}
}
Err(nom::Err::Error(CustomError::MyError(MyError(
"NoKeywordKey".into(),
))))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn optval<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
recognize(many_till(
anychar,
peek(optval_end(input.get_bracket_depth())),
))(input)
}
const fn optval_end(
starting_bracket_depth: BracketDepth,
) -> impl for<'s> Fn(OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
move |input: OrgSource<'_>| _optval_end(input, starting_bracket_depth)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn _optval_end<'s>(
input: OrgSource<'s>,
starting_bracket_depth: BracketDepth,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let current_depth = input.get_bracket_depth() - starting_bracket_depth;
if current_depth < 0 {
// This shouldn't be possible because if depth is 0 then a closing bracket should end the opval.
unreachable!("Exceeded optval bracket depth.")
}
if current_depth == 0 {
let close_bracket = tag::<_, _, CustomError<_>>("]")(input);
if close_bracket.is_ok() {
return close_bracket;
}
}
tag("\n")(input)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn export_keyword<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
recognize(tuple((
tag_no_case("attr_"),
take_while1(|c: char| c.is_alphanumeric() || "-_".contains(c)),
)))(input)
}

View File

@@ -5,7 +5,6 @@ use nom::character::complete::anychar;
use nom::character::complete::line_ending;
use nom::character::complete::none_of;
use nom::character::complete::one_of;
use nom::character::complete::space0;
use nom::combinator::peek;
use nom::combinator::recognize;
use nom::combinator::verify;
@@ -14,6 +13,7 @@ use nom::multi::many_till;
use nom::sequence::tuple;
use super::org_source::OrgSource;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
use crate::error::CustomError;
use crate::error::MyError;
@@ -36,7 +36,8 @@ pub fn latex_fragment<'r, 's>(
parser_with_context!(dollar_char_fragment)(context),
parser_with_context!(bordered_dollar_fragment)(context),
))(input)?;
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,
@@ -202,17 +203,13 @@ fn bordered_dollar_fragment<'r, 's>(
// TODO: I'm assuming I should be peeking at the borders but the documentation is not clear. Test to figure out.
let (_, _) = peek(parser_with_context!(open_border)(context))(remaining)?;
// TODO: As an optimization it would be nice to exit early upon hitting the 3rd line break
let (remaining, _) = verify(
recognize(many_till(
anychar,
peek(alt((
parser_with_context!(exit_matcher_parser)(context),
tag("$"),
))),
)),
|body: &OrgSource<'_>| Into::<&str>::into(body).lines().take(4).count() <= 3,
)(remaining)?;
let (remaining, _) = recognize(many_till(
anychar,
peek(alt((
parser_with_context!(exit_matcher_parser)(context),
tag("$"),
))),
))(remaining)?;
let (_, _) = peek(parser_with_context!(close_border)(context))(remaining)?;
let (remaining, _) = tag("$")(remaining)?;

View File

@@ -374,3 +374,9 @@ impl<'s> Source<'s> for Timestamp<'s> {
self.source
}
}
impl<'s> Source<'s> for PlainText<'s> {
fn get_source(&'s self) -> &'s str {
self.source
}
}

View File

@@ -33,7 +33,7 @@ pub fn standard_set_object<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Object<'s>> {
alt((
let (remaining, object) = alt((
map(parser_with_context!(timestamp)(context), Object::Timestamp),
map(parser_with_context!(subscript)(context), Object::Subscript),
map(
@@ -82,7 +82,8 @@ pub fn standard_set_object<'r, 's>(
map(parser_with_context!(angle_link)(context), Object::AngleLink),
map(parser_with_context!(org_macro)(context), Object::OrgMacro),
map(parser_with_context!(plain_text)(context), Object::PlainText),
))(input)
))(input)?;
Ok((remaining, object))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
@@ -90,7 +91,7 @@ pub fn minimal_set_object<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Object<'s>> {
alt((
let (remaining, object) = alt((
map(parser_with_context!(subscript)(context), Object::Subscript),
map(
parser_with_context!(superscript)(context),
@@ -103,7 +104,8 @@ pub fn minimal_set_object<'r, 's>(
),
parser_with_context!(text_markup)(context),
map(parser_with_context!(plain_text)(context), Object::PlainText),
))(input)
))(input)?;
Ok((remaining, object))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
@@ -111,7 +113,7 @@ pub fn any_object_except_plain_text<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Object<'s>> {
alt((
let (remaining, object) = alt((
map(parser_with_context!(timestamp)(context), Object::Timestamp),
map(parser_with_context!(subscript)(context), Object::Subscript),
map(
@@ -159,7 +161,8 @@ pub fn any_object_except_plain_text<'r, 's>(
map(parser_with_context!(plain_link)(context), Object::PlainLink),
map(parser_with_context!(angle_link)(context), Object::AngleLink),
map(parser_with_context!(org_macro)(context), Object::OrgMacro),
))(input)
))(input)?;
Ok((remaining, object))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
@@ -168,7 +171,7 @@ pub fn regular_link_description_object_set<'r, 's>(
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Object<'s>> {
// TODO: It can also contain another link, but only when it is a plain or angle link. It can contain square brackets, but not ]]
alt((
let (remaining, object) = alt((
map(
parser_with_context!(export_snippet)(context),
Object::ExportSnippet,
@@ -187,5 +190,40 @@ pub fn regular_link_description_object_set<'r, 's>(
),
map(parser_with_context!(org_macro)(context), Object::OrgMacro),
parser_with_context!(minimal_set_object)(context),
))(input)
))(input)?;
Ok((remaining, object))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn table_cell_set_object<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Object<'s>> {
let (remaining, object) = alt((
map(parser_with_context!(citation)(context), Object::Citation),
map(
parser_with_context!(export_snippet)(context),
Object::ExportSnippet,
),
map(
parser_with_context!(footnote_reference)(context),
Object::FootnoteReference,
),
map(parser_with_context!(radio_link)(context), Object::RadioLink),
map(
parser_with_context!(regular_link)(context),
Object::RegularLink,
),
map(parser_with_context!(plain_link)(context), Object::PlainLink),
map(parser_with_context!(angle_link)(context), Object::AngleLink),
map(parser_with_context!(org_macro)(context), Object::OrgMacro),
map(
parser_with_context!(radio_target)(context),
Object::RadioTarget,
),
map(parser_with_context!(target)(context), Object::Target),
map(parser_with_context!(timestamp)(context), Object::Timestamp),
parser_with_context!(minimal_set_object)(context),
))(input)?;
Ok((remaining, object))
}

View File

@@ -8,7 +8,9 @@ use nom::multi::many0;
use nom::multi::separated_list0;
use super::org_source::OrgSource;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
use crate::error::CustomError;
use crate::error::Res;
use crate::parser::object::OrgMacro;
use crate::parser::parser_with_context::parser_with_context;
@@ -24,6 +26,8 @@ pub fn org_macro<'r, 's>(
let (remaining, macro_name) = org_macro_name(context, remaining)?;
let (remaining, macro_args) = opt(parser_with_context!(org_macro_args)(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((
@@ -84,6 +88,11 @@ fn org_macro_arg<'r, 's>(
}
if next_char == '\\' {
escaping = true;
if peek(tag::<_, _, CustomError<_>>(")"))(new_remaining).is_ok() {
// Special case for backslash at the end of a macro
remaining = new_remaining;
break;
}
}
if next_char == ',' || next_char == ')' {
break;

View File

@@ -11,15 +11,28 @@ use nom::Slice;
use crate::error::CustomError;
use crate::error::MyError;
#[derive(Debug, Copy, Clone)]
pub type BracketDepth = i16;
#[derive(Copy, Clone)]
pub struct OrgSource<'s> {
full_source: &'s str,
start: usize,
end: usize, // exclusive
start_of_line: usize,
bracket_depth: BracketDepth, // []
brace_depth: BracketDepth, // {}
parenthesis_depth: BracketDepth, // ()
preceding_character: Option<char>,
}
impl<'s> std::fmt::Debug for OrgSource<'s> {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
f.debug_tuple("OrgSource")
.field(&Into::<&str>::into(self))
.finish()
}
}
impl<'s> OrgSource<'s> {
/// Returns a wrapped string that keeps track of values we need for parsing org-mode.
///
@@ -31,6 +44,9 @@ impl<'s> OrgSource<'s> {
end: input.len(),
start_of_line: 0,
preceding_character: None,
bracket_depth: 0,
brace_depth: 0,
parenthesis_depth: 0,
}
}
@@ -56,6 +72,18 @@ impl<'s> OrgSource<'s> {
assert!(other.end <= self.end);
self.slice(..(other.start - self.start))
}
pub fn get_bracket_depth(&self) -> BracketDepth {
self.bracket_depth
}
pub fn get_brace_depth(&self) -> BracketDepth {
self.brace_depth
}
pub fn get_parenthesis_depth(&self) -> BracketDepth {
self.parenthesis_depth
}
}
impl<'s> InputTake for OrgSource<'s> {
@@ -119,10 +147,36 @@ where
}
let skipped_text = &self.full_source[self.start..new_start];
let start_of_line = skipped_text
.rfind('\n')
.map(|idx| self.start + idx + 1)
.unwrap_or(self.start_of_line);
let mut start_of_line = self.start_of_line;
let mut bracket_depth = self.bracket_depth;
let mut brace_depth = self.brace_depth;
let mut parenthesis_depth = self.parenthesis_depth;
for (offset, byte) in skipped_text.bytes().enumerate() {
match byte {
b'\n' => {
start_of_line = self.start + offset + 1;
}
b'[' => {
bracket_depth += 1;
}
b']' => {
bracket_depth -= 1;
}
b'{' => {
brace_depth += 1;
}
b'}' => {
brace_depth -= 1;
}
b'(' => {
parenthesis_depth += 1;
}
b')' => {
parenthesis_depth -= 1;
}
_ => {}
};
}
OrgSource {
full_source: self.full_source,
@@ -130,6 +184,9 @@ where
end: new_end,
start_of_line,
preceding_character: skipped_text.chars().last(),
bracket_depth,
brace_depth,
parenthesis_depth,
}
}
}
@@ -246,7 +303,9 @@ impl<'s> InputTakeAtPosition for OrgSource<'s> {
}
}
pub fn convert_error(err: nom::Err<CustomError<OrgSource<'_>>>) -> nom::Err<CustomError<&str>> {
pub fn convert_error<'a, I: Into<CustomError<&'a str>>>(
err: nom::Err<I>,
) -> nom::Err<CustomError<&'a str>> {
match err {
nom::Err::Incomplete(needed) => nom::Err::Incomplete(needed),
nom::Err::Error(err) => nom::Err::Error(err.into()),
@@ -369,4 +428,19 @@ mod tests {
assert_eq!(input.get_preceding_character(), None);
assert_eq!(input.slice(8..).get_preceding_character(), Some('💛'));
}
#[test]
fn depth() {
let input = OrgSource::new("[][()][({)]}}}}");
assert_eq!(input.get_bracket_depth(), 0);
assert_eq!(input.get_brace_depth(), 0);
assert_eq!(input.get_parenthesis_depth(), 0);
assert_eq!(input.slice(4..).get_bracket_depth(), 1);
assert_eq!(input.slice(4..).get_brace_depth(), 0);
assert_eq!(input.slice(4..).get_parenthesis_depth(), 1);
assert_eq!(input.slice(4..).slice(6..).get_bracket_depth(), 1);
assert_eq!(input.slice(4..).slice(6..).get_brace_depth(), 1);
assert_eq!(input.slice(4..).slice(6..).get_parenthesis_depth(), 0);
assert_eq!(input.slice(14..).get_brace_depth(), -2);
}
}

View File

@@ -110,10 +110,9 @@ impl<'r, 's> ContextTree<'r, 's> {
pub enum ContextElement<'r, 's> {
/// Stores a parser that indicates that children should exit upon matching an exit matcher.
ExitMatcherNode(ExitMatcherNode<'r>),
Context(&'r str),
/// Stores the name of the greater block.
GreaterBlock(&'s str),
/// Stores the name of the current element to prevent directly nesting elements of the same type.
Context(&'r str),
/// Indicates if elements should consume the whitespace after them.
ConsumeTrailingWhitespace(bool),
@@ -124,71 +123,6 @@ pub enum ContextElement<'r, 's> {
/// org-mode document since text needs to be re-parsed to look for
/// radio links matching the contents of radio targets.
RadioTarget(Vec<&'r Vec<Object<'s>>>),
/// Stores the current bracket depth inside a footnote reference's definition.
///
/// The definition inside a footnote reference must have balanced
/// brackets [] inside the definition, so this stores the amount
/// of opening brackets subtracted by the amount of closing
/// brackets within the definition must equal zero.
///
/// A reference to the position in the string is also included so
/// unbalanced brackets can be detected in the middle of an
/// object.
FootnoteReferenceDefinition(FootnoteReferenceDefinition<'s>),
/// Stores the current bracket depth inside a citation.
///
/// The global prefix, global suffix, key prefix, and key suffix
/// inside a footnote reference must have balanced brackets []
/// inside the definition, so this stores the amount of opening
/// brackets subtracted by the amount of closing brackets within
/// the definition must equal zero. None of the prefixes or
/// suffixes can be nested inside each other so we can use a
/// single type for this without conflict.
///
/// A reference to the position in the string is also included so
/// unbalanced brackets can be detected in the middle of an
/// object.
CitationBracket(CitationBracket<'s>),
/// Stores the current bracket or parenthesis depth inside an inline babel call.
///
/// Inside an inline babel call the headers must have balanced
/// parentheses () and the arguments must have balanced brackets
/// [], so this stores the amount of opening brackets subtracted
/// by the amount of closing brackets within the definition must
/// equal zero.
///
/// A reference to the position in the string is also included so
/// unbalanced brackets can be detected in the middle of an
/// object.
BabelHeaderBracket(BabelHeaderBracket<'s>),
/// Stores the current bracket or parenthesis depth inside an inline babel call.
///
/// Inside an inline babel call the headers must have balanced
/// parentheses () and the arguments must have balanced brackets
/// [], so this stores the amount of opening brackets subtracted
/// by the amount of closing brackets within the definition must
/// equal zero.
///
/// A reference to the position in the string is also included so
/// unbalanced brackets can be detected in the middle of an
/// object.
InlineSourceBlockBracket(InlineSourceBlockBracket<'s>),
/// Stores the current bracket or parenthesis depth inside a
/// superscript or superscript.
///
/// Inside the braces of a subscript or superscript there must be
/// balanced braces {}, so this stores the amount of opening
/// braces subtracted by the amount of closing braces within the
/// definition must equal zero.
///
/// A reference to the position in the string is also included so
/// unbalanced braces can be detected in the middle of an object.
SubscriptSuperscriptBrace(SubscriptSuperscriptBrace<'s>),
}
pub struct ExitMatcherNode<'r> {
@@ -196,36 +130,6 @@ pub struct ExitMatcherNode<'r> {
pub class: ExitClass,
}
#[derive(Debug)]
pub struct FootnoteReferenceDefinition<'s> {
pub position: OrgSource<'s>,
pub depth: usize,
}
#[derive(Debug)]
pub struct CitationBracket<'s> {
pub position: OrgSource<'s>,
pub depth: usize,
}
#[derive(Debug)]
pub struct BabelHeaderBracket<'s> {
pub position: OrgSource<'s>,
pub depth: usize,
}
#[derive(Debug)]
pub struct InlineSourceBlockBracket<'s> {
pub position: OrgSource<'s>,
pub depth: usize,
}
#[derive(Debug)]
pub struct SubscriptSuperscriptBrace<'s> {
pub position: OrgSource<'s>,
pub depth: usize,
}
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");

View File

@@ -7,6 +7,7 @@ use nom::character::complete::one_of;
use nom::combinator::eof;
use nom::combinator::peek;
use nom::combinator::recognize;
use nom::combinator::verify;
use nom::multi::many_till;
use super::org_source::OrgSource;
@@ -23,6 +24,33 @@ use crate::parser::util::exit_matcher_parser;
use crate::parser::util::get_consumed;
use crate::parser::util::WORD_CONSTITUENT_CHARACTERS;
// TODO: Make this a user-provided variable corresponding to elisp's org-link-parameters
const ORG_LINK_PARAMETERS: [&'static str; 23] = [
"id",
"eww",
"rmail",
"mhe",
"irc",
"info",
"gnus",
"docview",
"bibtex",
"bbdb",
"w3m",
"doi",
"file+sys",
"file+emacs",
"shell",
"news",
"mailto",
"https",
"http",
"ftp",
"help",
"file",
"elisp",
];
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn plain_link<'r, 's>(
context: Context<'r, 's>,
@@ -73,36 +101,19 @@ pub fn protocol<'r, 's>(
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
// TODO: This should be defined by org-link-parameters
let (remaining, proto) = alt((
alt((
tag_no_case("id"),
tag_no_case("eww"),
tag_no_case("rmail"),
tag_no_case("mhe"),
tag_no_case("irc"),
tag_no_case("info"),
tag_no_case("gnus"),
tag_no_case("docview"),
tag_no_case("bibtex"),
tag_no_case("bbdb"),
tag_no_case("w3m"),
)),
alt((
tag_no_case("doi"),
tag_no_case("file+sys"),
tag_no_case("file+emacs"),
tag_no_case("shell"),
tag_no_case("news"),
tag_no_case("mailto"),
tag_no_case("https"),
tag_no_case("http"),
tag_no_case("ftp"),
tag_no_case("help"),
tag_no_case("file"),
tag_no_case("elisp"),
)),
))(input)?;
Ok((remaining, proto))
for link_parameter in ORG_LINK_PARAMETERS {
let result = tag_no_case::<_, _, CustomError<_>>(link_parameter)(input);
match result {
Ok((remaining, ent)) => {
return Ok((remaining, ent));
}
Err(_) => {}
}
}
Err(nom::Err::Error(CustomError::MyError(MyError(
"NoLinkProtocol".into(),
))))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
@@ -119,7 +130,11 @@ fn path_plain<'r, 's>(
let exit_matcher = parser_with_context!(exit_matcher_parser)(&parser_context);
let (remaining, path) = recognize(many_till(anychar, peek(exit_matcher)))(input)?;
let (remaining, path) = recognize(verify(
many_till(anychar, peek(exit_matcher)),
|(children, _exit_contents)| !children.is_empty(),
))(input)?;
Ok((remaining, path))
}
@@ -128,5 +143,10 @@ fn path_plain_end<'r, 's>(
_context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
recognize(one_of(" \t\r\n()[]<>"))(input)
recognize(many_till(
verify(anychar, |c| {
*c != '/' && (c.is_ascii_punctuation() || c.is_whitespace())
}),
one_of(" \t\r\n()[]<>"),
))(input)
}

View File

@@ -6,19 +6,24 @@ use nom::character::complete::one_of;
use nom::character::complete::space0;
use nom::character::complete::space1;
use nom::combinator::eof;
use nom::combinator::not;
use nom::combinator::opt;
use nom::combinator::peek;
use nom::combinator::recognize;
use nom::combinator::verify;
use nom::multi::many0;
use nom::multi::many1;
use nom::multi::many_till;
use nom::sequence::tuple;
use super::greater_element::PlainList;
use super::greater_element::PlainListItem;
use super::object_parser::standard_set_object;
use super::org_source::OrgSource;
use super::parser_with_context::parser_with_context;
use super::util::non_whitespace_character;
use super::Context;
use super::Object;
use crate::error::CustomError;
use crate::error::MyError;
use crate::error::Res;
@@ -33,13 +38,14 @@ use crate::parser::util::maybe_consume_trailing_whitespace_if_not_exiting;
use crate::parser::util::start_of_line;
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn detect_plain_list<'r, 's>(
_context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, ()> {
// TODO: Add support for plain list items that do not have content on the first line.
pub fn detect_plain_list<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s>, ()> {
if verify(
tuple((start_of_line, space0, bullet, space1)),
tuple((
start_of_line,
space0,
bullet,
alt((space1, line_ending, eof)),
)),
|(_start, indent, bull, _after_whitespace)| {
Into::<&str>::into(bull) != "*" || indent.len() > 0
},
@@ -60,6 +66,7 @@ pub fn plain_list<'r, 's>(
) -> Res<OrgSource<'s>, PlainList<'s>> {
let parser_context = context
.with_additional_node(ContextElement::Context("plain list"))
.with_additional_node(ContextElement::ConsumeTrailingWhitespace(true))
.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
class: ExitClass::Beta,
exit_matcher: &plain_list_end,
@@ -134,26 +141,33 @@ pub fn plain_list_item<'r, 's>(
Into::<&str>::into(bull) != "*" || indent_level > 0
})(remaining)?;
// TODO: This isn't taking into account items that immediately line break and then have contents
let (remaining, maybe_tag) = opt(tuple((
space1,
parser_with_context!(item_tag)(context),
tag(" ::"),
)))(remaining)?;
let maybe_contentless_item: Res<OrgSource<'_>, OrgSource<'_>> =
alt((eof, line_ending))(remaining);
peek(recognize(tuple((many0(blank_line), eof))))(remaining);
match maybe_contentless_item {
Ok((rem, _ws)) => {
let source = get_consumed(input, rem);
Ok((_rem, _ws)) => {
let (remaining, _trailing_ws) = opt(blank_line)(remaining)?;
let source = get_consumed(input, remaining);
return Ok((
rem,
remaining,
PlainListItem {
source: source.into(),
indentation: indent_level,
bullet: bull.into(),
tag: maybe_tag
.map(|(_ws, item_tag, _divider)| item_tag)
.unwrap_or(Vec::new()),
children: Vec::new(),
},
));
}
Err(_) => {}
};
let (remaining, _ws) = space1(remaining)?;
let (remaining, _ws) = item_tag_post_gap(context, remaining)?;
let exit_matcher = plain_list_item_end(indent_level);
let parser_context = context
.with_additional_node(ContextElement::ConsumeTrailingWhitespace(true))
@@ -162,14 +176,24 @@ pub fn plain_list_item<'r, 's>(
exit_matcher: &exit_matcher,
}));
let (remaining, (children, _exit_contents)) = verify(
many_till(
parser_with_context!(element(true))(&parser_context),
parser_with_context!(exit_matcher_parser)(&parser_context),
),
|(children, _exit_contents)| !children.is_empty(),
let (mut remaining, (mut children, _exit_contents)) = many_till(
include_input(parser_with_context!(element(true))(&parser_context)),
parser_with_context!(exit_matcher_parser)(&parser_context),
)(remaining)?;
if !children.is_empty() && !context.should_consume_trailing_whitespace() {
let final_item_context =
parser_context.with_additional_node(ContextElement::ConsumeTrailingWhitespace(false));
let (final_child_start, _original_final_child) = children
.pop()
.expect("if-statement already checked that children was non-empty.");
let (remain, reparsed_final_element) = include_input(parser_with_context!(element(true))(
&final_item_context,
))(final_child_start)?;
remaining = remain;
children.push(reparsed_final_element);
}
let (remaining, _trailing_ws) =
maybe_consume_trailing_whitespace_if_not_exiting(context, remaining)?;
@@ -180,11 +204,26 @@ pub fn plain_list_item<'r, 's>(
source: source.into(),
indentation: indent_level,
bullet: bull.into(),
children,
tag: maybe_tag
.map(|(_ws, item_tag, _divider)| item_tag)
.unwrap_or(Vec::new()),
children: children.into_iter().map(|(_start, item)| item).collect(),
},
));
}
fn include_input<'s, F, O>(
mut inner: F,
) -> impl FnMut(OrgSource<'s>) -> Res<OrgSource<'s>, (OrgSource<'s>, O)>
where
F: FnMut(OrgSource<'s>) -> Res<OrgSource<'s>, O>,
{
move |input: OrgSource<'_>| {
let (remaining, output) = inner(input)?;
Ok((remaining, (input, output)))
}
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn bullet<'s>(i: OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
alt((
@@ -262,6 +301,60 @@ fn _line_indented_lte<'r, 's>(
Ok(matched)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn item_tag<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Vec<Object<'s>>> {
let parser_context =
context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
class: ExitClass::Gamma,
exit_matcher: &item_tag_end,
}));
let (remaining, (children, _exit_contents)) = verify(
many_till(
// TODO: Should this be using a different set like the minimal set?
parser_with_context!(standard_set_object)(&parser_context),
parser_with_context!(exit_matcher_parser)(&parser_context),
),
|(children, _exit_contents)| !children.is_empty(),
)(input)?;
Ok((remaining, children))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn item_tag_end<'r, 's>(
_context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
recognize(alt((
line_ending,
tag(" :: "),
recognize(tuple((tag(" ::"), alt((line_ending, eof))))),
)))(input)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn item_tag_post_gap<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
verify(
recognize(tuple((
alt((blank_line, space0)),
many_till(
blank_line,
alt((
peek(recognize(not(blank_line))),
peek(recognize(tuple((many0(blank_line), eof)))),
parser_with_context!(exit_matcher_parser)(context),
)),
),
))),
|gap| gap.len() > 0,
)(input)
}
#[cfg(test)]
mod tests {
use super::*;
@@ -419,4 +512,36 @@ dolar"#,
"#
);
}
#[test]
fn detect_line_break() {
let input = OrgSource::new(
r#"+
"#,
);
let result = detect_plain_list(input);
assert!(result.is_ok());
}
#[test]
fn detect_eof() {
let input = OrgSource::new(r#"+"#);
let result = detect_plain_list(input);
assert!(result.is_ok());
}
#[test]
fn detect_no_gap() {
let input = OrgSource::new(r#"+foo"#);
let result = detect_plain_list(input);
// Since there is no whitespace after the '+' this is a paragraph, not a plain list.
assert!(result.is_err());
}
#[test]
fn detect_with_gap() {
let input = OrgSource::new(r#"+ foo"#);
let result = detect_plain_list(input);
assert!(result.is_ok());
}
}

View File

@@ -2,13 +2,14 @@ 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::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::opt;
use nom::combinator::recognize;
use nom::combinator::verify;
use nom::multi::many_till;
use nom::sequence::tuple;
@@ -23,7 +24,6 @@ use crate::parser::greater_element::PropertyDrawer;
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_text::plain_text;
use crate::parser::util::exit_matcher_parser;
use crate::parser::util::get_consumed;
use crate::parser::util::immediate_in_section;
@@ -147,11 +147,16 @@ fn node_property_name<'r, 's>(
}));
let (remaining, name) = recognize(tuple((
map(parser_with_context!(plain_text)(&parser_context), |pt| {
pt.source
}),
verify(
many_till(
anychar,
parser_with_context!(exit_matcher_parser)(&parser_context),
),
|(children, _exit_contents)| !children.is_empty(),
),
opt(tag("+")),
)))(input)?;
Ok((remaining, name))
}

View File

@@ -6,6 +6,7 @@ use nom::combinator::verify;
use nom::multi::many_till;
use super::org_source::OrgSource;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
use super::Object;
use crate::error::CustomError;
@@ -104,7 +105,8 @@ pub fn radio_target<'r, 's>(
)(remaining)?;
let (remaining, _closing) = tag(">>>")(remaining)?;
let (remaining, _trailing_whitespace) = space0(remaining)?;
let (remaining, _trailing_whitespace) =
maybe_consume_object_trailing_whitespace_if_not_exiting(context, remaining)?;
let source = get_consumed(input, remaining);
Ok((
remaining,

View File

@@ -3,13 +3,13 @@ use nom::bytes::complete::escaped;
use nom::bytes::complete::tag;
use nom::bytes::complete::take_till1;
use nom::character::complete::one_of;
use nom::character::complete::space0;
use nom::combinator::verify;
use nom::multi::many_till;
use super::org_source::OrgSource;
use super::parser_with_context::parser_with_context;
use super::util::get_consumed;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
use super::Object;
use super::RegularLink;
@@ -39,7 +39,8 @@ pub fn regular_link_without_description<'r, 's>(
let (remaining, _opening_bracket) = tag("[[")(input)?;
let (remaining, _path) = pathreg(context, remaining)?;
let (remaining, _closing_bracket) = tag("]]")(remaining)?;
let (remaining, _trailing_whitespace) = 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 +60,8 @@ pub fn regular_link_with_description<'r, 's>(
let (remaining, _closing_bracket) = tag("][")(remaining)?;
let (remaining, _description) = description(context, remaining)?;
let (remaining, _closing_bracket) = tag("]]")(remaining)?;
let (remaining, _trailing_whitespace) = space0(remaining)?;
let (remaining, _trailing_whitespace) =
maybe_consume_object_trailing_whitespace_if_not_exiting(context, remaining)?;
let source = get_consumed(input, remaining);
Ok((
remaining,

View File

@@ -35,44 +35,6 @@ pub struct TextWithProperties<'s> {
pub properties: Vec<Token<'s>>,
}
impl<'s> TextWithProperties<'s> {
pub fn unquote(&self) -> Result<String, Box<dyn std::error::Error>> {
let mut out = String::with_capacity(self.text.len());
if !self.text.starts_with(r#"""#) {
return Err("Quoted text does not start with quote.".into());
}
if !self.text.ends_with(r#"""#) {
return Err("Quoted text does not end with quote.".into());
}
let interior_text = &self.text[1..(self.text.len() - 1)];
let mut state = ParseState::Normal;
for current_char in interior_text.chars().into_iter() {
state = match (state, current_char) {
(ParseState::Normal, '\\') => ParseState::Escape,
(ParseState::Normal, _) => {
out.push(current_char);
ParseState::Normal
}
(ParseState::Escape, 'n') => {
out.push('\n');
ParseState::Normal
}
(ParseState::Escape, '\\') => {
out.push('\\');
ParseState::Normal
}
(ParseState::Escape, '"') => {
out.push('"');
ParseState::Normal
}
_ => todo!(),
};
}
Ok(out)
}
}
enum ParseState {
Normal,
Escape,
@@ -82,28 +44,28 @@ impl<'s> Token<'s> {
pub 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 {:?}", self)),
_ => 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>> {
Ok(match self {
Token::List(children) => Ok(children),
_ => Err(format!("wrong token type {:?}", self)),
_ => Err(format!("wrong token type, expected list: {:?}", self)),
}?)
}
pub 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 {:?}", self)),
_ => Err(format!("wrong token type, expected atom: {:?}", self)),
}?)
}
pub 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 {:?}", self)),
_ => Err(format!("wrong token type, expected text: {:?}", self)),
}?)
}
@@ -133,6 +95,42 @@ impl<'s> Token<'s> {
}
}
pub 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());
}
if !text.ends_with(r#"""#) {
return Err("Quoted text does not end with quote.".into());
}
let interior_text = &text[1..(text.len() - 1)];
let mut state = ParseState::Normal;
for current_char in interior_text.chars().into_iter() {
state = match (state, current_char) {
(ParseState::Normal, '\\') => ParseState::Escape,
(ParseState::Normal, _) => {
out.push(current_char);
ParseState::Normal
}
(ParseState::Escape, 'n') => {
out.push('\n');
ParseState::Normal
}
(ParseState::Escape, '\\') => {
out.push('\\');
ParseState::Normal
}
(ParseState::Escape, '"') => {
out.push('"');
ParseState::Normal
}
_ => todo!(),
};
}
Ok(out)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn sexp_with_padding<'s>(input: &'s str) -> Res<&'s str, Token<'s>> {
let (remaining, _) = multispace0(input)?;

View File

@@ -1,10 +1,10 @@
use nom::branch::alt;
use nom::bytes::complete::tag;
use nom::character::complete::space0;
use nom::combinator::recognize;
use nom::sequence::tuple;
use super::org_source::OrgSource;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
use crate::error::Res;
use crate::parser::parser_with_context::parser_with_context;
@@ -23,12 +23,13 @@ pub fn statistics_cookie<'r, 's>(
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn percent_statistics_cookie<'r, 's>(
_context: Context<'r, 's>,
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, StatisticsCookie<'s>> {
let (remaining, source) =
recognize(tuple((tag("["), nom::character::complete::u64, tag("%]"))))(input)?;
let (remaining, _) = space0(remaining)?;
let (remaining, _trailing_whitespace) =
maybe_consume_object_trailing_whitespace_if_not_exiting(context, remaining)?;
Ok((
remaining,
StatisticsCookie {
@@ -39,7 +40,7 @@ pub fn percent_statistics_cookie<'r, 's>(
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn fraction_statistics_cookie<'r, 's>(
_context: Context<'r, 's>,
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, StatisticsCookie<'s>> {
let (remaining, source) = recognize(tuple((
@@ -49,7 +50,8 @@ pub fn fraction_statistics_cookie<'r, 's>(
nom::character::complete::u64,
tag("]"),
)))(input)?;
let (remaining, _) = space0(remaining)?;
let (remaining, _trailing_whitespace) =
maybe_consume_object_trailing_whitespace_if_not_exiting(context, remaining)?;
Ok((
remaining,
StatisticsCookie {

View File

@@ -2,7 +2,6 @@ use nom::branch::alt;
use nom::bytes::complete::tag;
use nom::character::complete::anychar;
use nom::character::complete::one_of;
use nom::character::complete::space0;
use nom::combinator::map;
use nom::combinator::not;
use nom::combinator::opt;
@@ -11,7 +10,9 @@ use nom::combinator::recognize;
use nom::combinator::verify;
use nom::multi::many_till;
use super::org_source::BracketDepth;
use super::org_source::OrgSource;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
use super::Object;
use crate::error::CustomError;
@@ -21,7 +22,6 @@ use crate::parser::exiting::ExitClass;
use crate::parser::object_parser::standard_set_object;
use crate::parser::parser_context::ContextElement;
use crate::parser::parser_context::ExitMatcherNode;
use crate::parser::parser_context::SubscriptSuperscriptBrace;
use crate::parser::parser_with_context::parser_with_context;
use crate::parser::util::exit_matcher_parser;
use crate::parser::util::get_consumed;
@@ -37,7 +37,8 @@ pub fn subscript<'r, 's>(
let (remaining, _) = tag("_")(input)?;
pre(context, input)?;
let (remaining, _body) = script_body(context, 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,
@@ -56,7 +57,8 @@ pub fn superscript<'r, 's>(
let (remaining, _) = tag("^")(input)?;
pre(context, input)?;
let (remaining, _body) = script_body(context, 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,
@@ -154,16 +156,11 @@ fn script_with_braces<'r, 's>(
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Vec<Object<'s>>> {
let (remaining, _) = tag("{")(input)?;
let parser_context = context
.with_additional_node(ContextElement::SubscriptSuperscriptBrace(
SubscriptSuperscriptBrace {
position: remaining.into(),
depth: 0,
},
))
.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
let exit_with_depth = script_with_braces_end(remaining.get_brace_depth());
let parser_context =
context.with_additional_node(ContextElement::ExitMatcherNode(ExitMatcherNode {
class: ExitClass::Gamma,
exit_matcher: &script_with_braces_end,
exit_matcher: &exit_with_depth,
}));
let (remaining, (children, _exit_contents)) = many_till(
@@ -175,49 +172,30 @@ fn script_with_braces<'r, 's>(
Ok((remaining, children))
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn script_with_braces_end<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let context_depth = get_bracket_depth(context)
.expect("This function should only be called from inside a subscript or superscript.");
let text_since_context_entry = get_consumed(context_depth.position, input);
let mut current_depth = context_depth.depth;
for c in Into::<&str>::into(text_since_context_entry).chars() {
match c {
'{' => {
current_depth += 1;
}
'}' if current_depth == 0 => {
panic!("Exceeded subscript or superscript brace depth.")
}
'}' if current_depth > 0 => {
current_depth -= 1;
}
_ => {}
}
fn script_with_braces_end(
starting_brace_depth: BracketDepth,
) -> impl for<'r, 's> Fn(Context<'r, 's>, OrgSource<'s>) -> Res<OrgSource<'s>, OrgSource<'s>> {
move |context: Context, input: OrgSource<'_>| {
_script_with_braces_end(context, input, starting_brace_depth)
}
if current_depth == 0 {
let close_bracket = tag::<&str, OrgSource<'_>, CustomError<OrgSource<'_>>>("}")(input);
if close_bracket.is_ok() {
return close_bracket;
}
}
return Err(nom::Err::Error(CustomError::MyError(MyError(
"Not a valid end for subscript or superscript.".into(),
))));
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
fn get_bracket_depth<'r, 's>(
context: Context<'r, 's>,
) -> Option<&'r SubscriptSuperscriptBrace<'s>> {
for node in context.iter() {
match node.get_data() {
ContextElement::SubscriptSuperscriptBrace(depth) => return Some(depth),
_ => {}
}
fn _script_with_braces_end<'r, 's>(
_context: Context<'r, 's>,
input: OrgSource<'s>,
starting_brace_depth: BracketDepth,
) -> Res<OrgSource<'s>, OrgSource<'s>> {
let current_depth = input.get_brace_depth() - starting_brace_depth;
if current_depth > 0 {
// Its impossible for the next character to end the subscript or superscript if we're any amount of braces deep
return Err(nom::Err::Error(CustomError::MyError(MyError(
"Not a valid end for subscript or superscript.".into(),
))));
}
None
if current_depth < 0 {
// This shouldn't be possible because if depth is 0 then a closing brace should end the subscript or superscript.
unreachable!("Exceeded subscript or superscript brace depth.")
}
tag("}")(input)
}

View File

@@ -12,14 +12,13 @@ use nom::multi::many1;
use nom::multi::many_till;
use nom::sequence::tuple;
use super::object_parser::table_cell_set_object;
use super::org_source::OrgSource;
use super::Context;
use crate::error::Res;
use crate::parser::exiting::ExitClass;
use crate::parser::greater_element::TableRow;
use crate::parser::lesser_element::TableCell;
use crate::parser::object::Object;
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;
@@ -162,14 +161,3 @@ fn org_mode_table_cell_end<'r, 's>(
) -> Res<OrgSource<'s>, OrgSource<'s>> {
recognize(tuple((space0, alt((tag("|"), peek(line_ending))))))(input)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn table_cell_set_object<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Object<'s>> {
not(|i| context.check_exit_matcher(i))(input)?;
parser_with_context!(minimal_set_object)(context)(input)
// TODO: add citations, export snippets, footnote references, links, macros, radio targets, targets, and timestamps.
}

View File

@@ -1,13 +1,13 @@
use nom::bytes::complete::tag;
use nom::character::complete::anychar;
use nom::character::complete::one_of;
use nom::character::complete::space0;
use nom::combinator::peek;
use nom::combinator::recognize;
use nom::combinator::verify;
use nom::multi::many_till;
use super::org_source::OrgSource;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
use crate::error::CustomError;
use crate::error::MyError;
@@ -49,7 +49,8 @@ pub fn target<'r, 's>(
))));
}
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((

View File

@@ -17,6 +17,7 @@ use tracing::span;
use super::org_source::OrgSource;
use super::radio_link::RematchObject;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
use crate::error::CustomError;
use crate::error::MyError;
@@ -204,7 +205,8 @@ fn _text_markup_object<'r, 's, 'x>(
}
let (remaining, _close) = text_markup_end_specialized(context, remaining)?;
let (remaining, _trailing_whitespace) = space0(remaining)?;
let (remaining, _trailing_whitespace) =
maybe_consume_object_trailing_whitespace_if_not_exiting(context, remaining)?;
Ok((remaining, children))
}
@@ -254,7 +256,8 @@ fn _text_markup_string<'r, 's, 'x>(
}
let (remaining, _close) = text_markup_end_specialized(context, remaining)?;
let (remaining, _trailing_whitespace) = space0(remaining)?;
let (remaining, _trailing_whitespace) =
maybe_consume_object_trailing_whitespace_if_not_exiting(context, remaining)?;
Ok((remaining, contents))
}
@@ -277,7 +280,7 @@ pub fn pre<'r, 's>(_context: Context<'r, 's>, input: OrgSource<'s>) -> Res<OrgSo
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn post<'r, 's>(_context: Context<'r, 's>, input: OrgSource<'s>) -> Res<OrgSource<'s>, ()> {
let (remaining, _) = alt((recognize(one_of(" \r\n\t-.,;:!?')}[\">")), line_ending))(input)?;
let (remaining, _) = alt((recognize(one_of(" \r\n\t-.,;:!?')}[\"")), line_ending))(input)?;
Ok((remaining, ()))
}

View File

@@ -3,7 +3,6 @@ use nom::bytes::complete::tag;
use nom::character::complete::anychar;
use nom::character::complete::digit1;
use nom::character::complete::one_of;
use nom::character::complete::space0;
use nom::character::complete::space1;
use nom::combinator::opt;
use nom::combinator::recognize;
@@ -12,6 +11,7 @@ use nom::multi::many_till;
use nom::sequence::tuple;
use super::org_source::OrgSource;
use super::util::maybe_consume_object_trailing_whitespace_if_not_exiting;
use super::Context;
use crate::error::Res;
use crate::parser::exiting::ExitClass;
@@ -49,7 +49,8 @@ fn diary_timestamp<'r, 's>(
let (remaining, _) = tag("<%%(")(input)?;
let (remaining, _body) = sexp(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((
@@ -112,7 +113,8 @@ fn active_timestamp<'r, 's>(
)))(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((
@@ -145,7 +147,8 @@ fn inactive_timestamp<'r, 's>(
)))(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((
@@ -166,7 +169,8 @@ fn active_date_range_timestamp<'r, 's>(
let (remaining, _separator) = tag("--")(remaining)?;
let (remaining, _second_timestamp) = active_timestamp(context, 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((
@@ -206,7 +210,8 @@ fn active_time_range_timestamp<'r, 's>(
)))(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((
@@ -227,7 +232,8 @@ fn inactive_date_range_timestamp<'r, 's>(
let (remaining, _separator) = tag("--")(remaining)?;
let (remaining, _second_timestamp) = inactive_timestamp(context, 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((
@@ -267,7 +273,8 @@ fn inactive_time_range_timestamp<'r, 's>(
)))(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((

View File

@@ -68,6 +68,18 @@ pub fn element_trailing_whitespace<'s>(input: OrgSource<'s>) -> Res<OrgSource<'s
alt((eof, recognize(many0(blank_line))))(input)
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn maybe_consume_object_trailing_whitespace_if_not_exiting<'r, 's>(
context: Context<'r, 's>,
input: OrgSource<'s>,
) -> Res<OrgSource<'s>, Option<OrgSource<'s>>> {
if exit_matcher_parser(context, input).is_err() {
opt(space0)(input)
} else {
Ok((input, None))
}
}
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
pub fn maybe_consume_trailing_whitespace_if_not_exiting<'r, 's>(
context: Context<'r, 's>,
@@ -155,3 +167,16 @@ pub fn not_yet_implemented() -> Res<OrgSource<'static>, ()> {
"Not implemented yet.".into(),
))));
}
#[allow(dead_code)]
#[cfg_attr(feature = "tracing", tracing::instrument(ret, level = "debug"))]
/// Text from the current point until the next line break or end of file
///
/// Useful for debugging.
pub fn text_until_eol<'r, 's>(
input: OrgSource<'s>,
) -> Result<&'s str, nom::Err<CustomError<OrgSource<'s>>>> {
let line = recognize(many_till(anychar, alt((line_ending, eof))))(input)
.map(|(_remaining, line)| Into::<&str>::into(line))?;
Ok(line.trim())
}

View File

@@ -1 +1,2 @@
#[cfg(feature = "compare")]
include!(concat!(env!("OUT_DIR"), "/tests.rs"));

View File

@@ -11,7 +11,7 @@ fn {name}() {{
let diff_result =
compare_document(&parsed_sexp, &rust_parsed).expect("Compare parsed documents.");
diff_result
.print()
.print(org_contents.as_str())
.expect("Print document parse tree diff.");
assert!(!diff_result.is_bad());
assert_eq!(remaining, "");