zig-codeblocks - pypi Package Compare versions

Comparing version

+14

-1

CHANGELOG.md

		@@ -8,2 +8,14 @@ # Changelog

		## [v0.1.2] - 2025-02-09

		### Added
		- Character literal highlighting

		### Changed
		- Public API functions can now operate on `bytes` objects
		- Improved code block extraction on Windows

		### Fixed
		- Multi-byte characters no longer derail the highlighter

		## [v0.1.1] - 2025-02-08
		@@ -20,2 +32,3 @@
		[v0.1.0]: https://github.com/trag1c/zig-codeblocks/releases/tag/v0.1.0
		[v0.1.1]: https://github.com/trag1c/ixia/compare/v0.1.0...v0.1.1
		[v0.1.1]: https://github.com/trag1c/ixia/compare/v0.1.0...v0.1.1
		[v0.1.2]: https://github.com/trag1c/ixia/compare/v0.1.1...v0.1.2

+1

-1

PKG-INFO

		Metadata-Version: 2.4
		Name: zig-codeblocks
		Version: 0.1.1
		Version: 0.1.2
		Summary: Zig ANSI syntax highlighting library
		@@ -5,0 +5,0 @@ Project-URL: repository, https://github.com/trag1c/zig-codeblocks

+1

-1

pyproject.toml

		[project]
		name = "zig-codeblocks"
		version = "0.1.1"
		version = "0.1.2"
		description = "Zig ANSI syntax highlighting library"
		@@ -5,0 +5,0 @@ readme = "README.md"

+16

-6

src/zig_codeblocks/formatting.py

		@@ -72,3 +72,5 @@ from __future__ import annotations
		ZIG_NUMERIC_TOKENS = frozenset({"integer", "float"})
		ZIG_STRING_TOKENS = frozenset({"string_content", "multiline_string", '"'})
		ZIG_STRING_TOKENS = frozenset(
		{"string_content", "multiline_string", '"', "'", "character_content"}
		)

		@@ -122,3 +124,3 @@ _KIND_MAPPINGS = {

		def _process_zig_tokens(source: str, tokens: Iterator[Token]) -> str:
		def _process_zig_tokens(source: bytes, tokens: Iterator[Token]) -> str:
		body: Body = []
		@@ -133,3 +135,3 @@ pointer = 0
		_adjust_reset(body)
		body.append(filler)
		body.append(filler.decode())
		pointer = token.byte_range.start
		@@ -170,12 +172,20 @@

		def highlight_zig_code(source: str) -> str:
		"""Return an ANSI syntax-highlighted version of the given Zig source code."""
		def highlight_zig_code(source: str \| bytes) -> str:
		"""
		Return an ANSI syntax-highlighted version of the given Zig source code.
		Assumes UTF-8 if source is `bytes`.
		"""
		if isinstance(source, str):
		source = source.encode()
		return _process_zig_tokens(source, tokenize_zig(source))


		def process_markdown(source: str, *, only_code: bool = False) -> str:
		def process_markdown(source: str \| bytes, *, only_code: bool = False) -> str:
		"""
		Return a Markdown source with Zig code blocks syntax-highlighted.
		If `only_code` is True, only processed Zig code blocks will be returned.
		Assumes UTF-8 if source is `bytes`.
		"""
		if isinstance(source, bytes):
		source = source.decode()
		zig_codeblocks = (
		@@ -182,0 +192,0 @@ block.body for block in extract_codeblocks(source) if block.lang == "zig"

+8

-7

src/zig_codeblocks/parsing.py

		@@ -10,3 +10,3 @@ import re
		CODE_BLOCK_PATTERN = re.compile(
		r"```(?:([A-Za-z0-9\-_\+\.#]+)\n+([^\n].+?)\|(.*?))```", re.DOTALL
		r"```(?:([A-Za-z0-9\-_\+\.#]+)(?:\r?\n)+([^\r\n].+?)\|(.*?))```", re.DOTALL
		)
		@@ -30,15 +30,16 @@

		def extract_codeblocks(source: str) -> Iterator[CodeBlock]:
		"""Yield CodeBlocks from a Markdown source."""
		def extract_codeblocks(source: str \| bytes) -> Iterator[CodeBlock]:
		"""Yield CodeBlocks from a Markdown source. Assumes UTF-8 if source is `bytes`."""
		if isinstance(source, bytes):
		source = source.decode()
		for m in CODE_BLOCK_PATTERN.finditer(source):
		lang, body, no_lang_body = m.groups()
		yield (
		CodeBlock(lang, body=body.strip("\n"))
		CodeBlock(lang, body=body.strip("\r\n"))
		if lang
		else CodeBlock(lang=None, body=no_lang_body.strip("\n"))
		else CodeBlock(lang=None, body=no_lang_body.strip("\r\n"))
		)


		def tokenize_zig(source: str) -> Iterator[Token]:
		src = source.encode()
		def tokenize_zig(src: bytes) -> Iterator[Token]:
		tree = ZIG_PARSER.parse(src)
		@@ -45,0 +46,0 @@ return _traverse(tree.root_node, src)

+6

-6

tests/test_parsing.py

		@@ -21,7 +21,8 @@ from pathlib import Path
		def test_codeblock_spacing_scenarios(file_name: str) -> None:
		src = (SOURCE_DIR / "spacing" / file_name).read_text()
		assert list(extract_codeblocks(src)) == [
		CodeBlock(lang="py", body="print(1)"),
		CodeBlock(lang="zig", body='const std = @import("std");'),
		]
		src = SOURCE_DIR / "spacing" / file_name
		for meth in (Path.read_text, Path.read_bytes):
		assert list(extract_codeblocks(meth(src))) == [
		CodeBlock(lang="py", body="print(1)"),
		CodeBlock(lang="zig", body='const std = @import("std");'),
		]

		@@ -42,5 +43,4 @@
		def test_codeblock_with_language(source: str, expected: tuple[str \| None, str]) -> None:
		print((source, expected))
		codeblocks = list(extract_codeblocks(f"```{source}```"))
		assert len(codeblocks) == 1
		assert codeblocks[0] == CodeBlock(*expected)

+1

-1

uv.lock

.coverage

Sorry, the diff of this file is not supported yet

-16

test.py

		import zig_codeblocks as zc

		src = """
		```zig
		/// The health status of a renderer. These must be shared across all
		/// renderers even if some states aren't reachable so that our API users
		/// can use the same enum for all renderers.
		``````zig
		pub const Health = enum(c_int) {
		healthy = 0,
		unhealthy = 1,
		};
		```
		"""

		print(list(zc.extract_codeblocks(src)))

Worsened metrics