[Docs] Use gen-files for generated docs content (#49587)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2026-07-25 14:43:21 +00:00
committed by GitHub
parent d1a8ba63d9
commit 3e74c60b9c
34 changed files with 515 additions and 861 deletions
-289
View File
@@ -1,289 +0,0 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import importlib.metadata
import importlib.util
import logging
import sys
import textwrap
import traceback
from argparse import SUPPRESS, Action, HelpFormatter
from collections.abc import Callable, Iterable
from importlib.machinery import ModuleSpec
from pathlib import Path
from typing import TYPE_CHECKING, Literal
from unittest.mock import MagicMock, patch
from pydantic_core import core_schema
logger = logging.getLogger("mkdocs")
ROOT_DIR = Path(__file__).parent.parent.parent.parent
ARGPARSE_DOC_DIR = ROOT_DIR / "docs/generated/argparse"
sys.path.insert(0, str(ROOT_DIR))
def mock_if_no_torch(mock_module: str, mock: MagicMock):
if not importlib.util.find_spec("torch"):
sys.modules[mock_module] = mock
# Mock custom op code
class MockCustomOp:
@staticmethod
def register(name):
def decorator(cls):
return cls
return decorator
class MockPluggableLayer:
@staticmethod
def register(name):
def decorator(cls):
return cls
return decorator
mock_if_no_torch("vllm._C", MagicMock())
mock_if_no_torch("vllm._C_stable_libtorch", MagicMock())
mock_if_no_torch(
"vllm.model_executor.custom_op",
MagicMock(CustomOp=MockCustomOp, PluggableLayer=MockPluggableLayer),
)
mock_if_no_torch(
"vllm.utils.torch_utils", MagicMock(direct_register_custom_op=lambda *a, **k: None)
)
# Mock any version checks by reading from compiled CI requirements
with open(ROOT_DIR / "requirements/test/cuda.txt") as f:
VERSIONS = dict(line.strip().split("==") for line in f if "==" in line)
importlib.metadata.version = lambda name: VERSIONS.get(name) or "0.0.0"
# Make torch.nn.Parameter safe to inherit from
mock_if_no_torch("torch.nn", MagicMock(Parameter=object))
# Mock torch.library.infer_schema for vllm.ir.ops.IrOpInplaceOverload.__init__
# We need to return the corresponding number of inputs, as IR infra will assert it
def get_outputs(native_fn: Callable) -> str:
"""
Extract output schema from function's return type annotation,
e.g. 'Tensor' or 'Tensor, Tensor'.
"""
import typing
return_type = typing.get_type_hints(native_fn)["return"]
origin = typing.get_origin(return_type)
arg_name = lambda a: a.__name__ if hasattr(a, "__name__") else str(a)
if origin is tuple:
args = typing.get_args(return_type)
return ", ".join(arg_name(arg) for arg in args)
else:
return f"{arg_name(return_type)}"
mock_if_no_torch(
"torch.library",
MagicMock(infer_schema=lambda fn, **k: f"(Tensor x) -> {get_outputs(fn)}"),
)
class PydanticMagicMock(MagicMock):
"""`MagicMock` that's able to generate pydantic-core schemas."""
def __init__(self, *args, **kwargs):
name = kwargs.get("name")
super().__init__(*args, **kwargs)
self.__spec__ = ModuleSpec(name, None)
def __get_pydantic_core_schema__(self, source_type, handler):
return core_schema.any_schema()
def auto_mock(module_name: str, attr: str, max_mocks: int = 100):
"""Function that automatically mocks missing modules during imports."""
logger.info("Importing %s from %s", attr, module_name)
for _ in range(max_mocks):
try:
module = importlib.import_module(module_name)
# First treat attr as an attr, then as a submodule
if hasattr(module, attr):
return getattr(module, attr)
return importlib.import_module(f"{module_name}.{attr}")
except ModuleNotFoundError as e:
assert e.name is not None
logger.info("Mocking %s for argparse doc generation", e.name)
sys.modules[e.name] = PydanticMagicMock(name=e.name)
except Exception:
logger.exception("Failed to import %s.%s", module_name, attr)
raise
raise ImportError(
f"Failed to import {module_name}.{attr} after mocking {max_mocks} imports"
)
bench_latency = auto_mock("vllm.benchmarks", "latency")
bench_mm_processor = auto_mock("vllm.benchmarks", "mm_processor")
bench_serve = auto_mock("vllm.benchmarks", "serve")
bench_sweep_plot = auto_mock("vllm.benchmarks.sweep.plot", "SweepPlotArgs")
bench_sweep_plot_pareto = auto_mock(
"vllm.benchmarks.sweep.plot_pareto", "SweepPlotParetoArgs"
)
bench_sweep_serve = auto_mock("vllm.benchmarks.sweep.serve", "SweepServeArgs")
bench_sweep_serve_workload = auto_mock(
"vllm.benchmarks.sweep.serve_workload", "SweepServeWorkloadArgs"
)
bench_throughput = auto_mock("vllm.benchmarks", "throughput")
AsyncEngineArgs = auto_mock("vllm.engine.arg_utils", "AsyncEngineArgs")
EngineArgs = auto_mock("vllm.engine.arg_utils", "EngineArgs")
ChatCommand = auto_mock("vllm.entrypoints.cli.openai", "ChatCommand")
CompleteCommand = auto_mock("vllm.entrypoints.cli.openai", "CompleteCommand")
RenderSubcommand = auto_mock("vllm.entrypoints.cli.launch", "RenderSubcommand")
openai_cli_args = auto_mock("vllm.entrypoints.openai", "cli_args")
openai_run_batch = auto_mock("vllm.entrypoints.openai", "run_batch")
if TYPE_CHECKING:
from vllm.utils.argparse_utils import FlexibleArgumentParser
else:
FlexibleArgumentParser = auto_mock(
"vllm.utils.argparse_utils", "FlexibleArgumentParser"
)
class MarkdownFormatter(HelpFormatter):
"""Custom formatter that generates markdown for argument groups."""
def __init__(self, prog: str, starting_heading_level: int = 3):
super().__init__(prog, max_help_position=sys.maxsize, width=sys.maxsize)
self._section_heading_prefix = "#" * starting_heading_level
self._argument_heading_prefix = "#" * (starting_heading_level + 1)
self._markdown_output = []
def start_section(self, heading: str):
if heading not in {"positional arguments", "options"}:
heading_md = f"\n{self._section_heading_prefix} {heading}\n\n"
self._markdown_output.append(heading_md)
def end_section(self):
pass
def add_text(self, text: str):
if text:
self._markdown_output.append(f"{text.strip()}\n\n")
def add_usage(self, usage, actions, groups, prefix=None):
pass
def add_arguments(self, actions: Iterable[Action]):
for action in actions:
if len(action.option_strings) == 0 or "--help" in action.option_strings:
continue
option_strings = f"`{'`, `'.join(action.option_strings)}`"
heading_md = f"{self._argument_heading_prefix} {option_strings}\n\n"
self._markdown_output.append(heading_md)
if action.choices or isinstance(action.metavar, list | tuple):
choices_iterable = action.choices or action.metavar
choices = f"`{'`, `'.join(str(c) for c in choices_iterable)}`"
self._markdown_output.append(f": Possible choices: {choices}\n\n")
if action.help:
help_dd = ":" + textwrap.indent(action.help, " ")[1:]
self._markdown_output.append(f"{help_dd}\n\n")
# None usually means the default is determined at runtime
if (default := action.default) != SUPPRESS and default is not None:
# Make empty string defaults visible
if default == "":
default = '""'
self._markdown_output.append(f": Default: `{default}`\n\n")
def format_help(self):
"""Return the formatted help as markdown."""
return "".join(self._markdown_output)
def create_parser(add_cli_args, **kwargs) -> FlexibleArgumentParser:
"""Create a parser for the given class with markdown formatting.
Args:
cls: The class to create a parser for
**kwargs: Additional keyword arguments to pass to `cls.add_cli_args`.
Returns:
FlexibleArgumentParser: A parser with markdown formatting for the class.
"""
try:
parser = FlexibleArgumentParser(add_json_tip=False)
parser.formatter_class = MarkdownFormatter
with patch("vllm.config.DeviceConfig.__post_init__"):
_parser = add_cli_args(parser, **kwargs)
except ModuleNotFoundError as e:
# Auto-mock runtime imports
if tb_list := traceback.extract_tb(e.__traceback__):
path = Path(tb_list[-1].filename).relative_to(ROOT_DIR)
auto_mock(module_name=".".join(path.parent.parts), attr=path.stem)
return create_parser(add_cli_args, **kwargs)
else:
raise e
# add_cli_args might be in-place so return parser if _parser is None
return _parser or parser
def on_startup(command: Literal["build", "gh-deploy", "serve"], dirty: bool):
logger.info("Generating argparse documentation")
logger.debug("Root directory: %s", ROOT_DIR.resolve())
logger.debug("Output directory: %s", ARGPARSE_DOC_DIR.resolve())
# Create the ARGPARSE_DOC_DIR if it doesn't exist
if not ARGPARSE_DOC_DIR.exists():
ARGPARSE_DOC_DIR.mkdir(parents=True)
# Create parsers to document
parsers = {
# Engine args
"engine_args": create_parser(EngineArgs.add_cli_args),
"async_engine_args": create_parser(
AsyncEngineArgs.add_cli_args, async_args_only=True
),
# CLI
"serve": create_parser(openai_cli_args.make_arg_parser),
"chat": create_parser(ChatCommand.add_cli_args),
"complete": create_parser(CompleteCommand.add_cli_args),
"launch_render": create_parser(RenderSubcommand.add_cli_args),
"run-batch": create_parser(openai_run_batch.make_arg_parser),
# Benchmark CLI
"bench_latency": create_parser(bench_latency.add_cli_args),
"bench_mm_processor": create_parser(bench_mm_processor.add_cli_args),
"bench_serve": create_parser(bench_serve.add_cli_args),
"bench_sweep_plot": create_parser(bench_sweep_plot.add_cli_args),
"bench_sweep_plot_pareto": create_parser(bench_sweep_plot_pareto.add_cli_args),
"bench_sweep_serve": create_parser(bench_sweep_serve.add_cli_args),
"bench_sweep_serve_workload": create_parser(
bench_sweep_serve_workload.add_cli_args
),
"bench_throughput": create_parser(bench_throughput.add_cli_args),
}
# Generate documentation for each parser
for stem, parser in parsers.items():
doc_path = ARGPARSE_DOC_DIR / f"{stem}.inc.md"
# Specify encoding for building on Windows
with open(doc_path, "w", encoding="utf-8") as f:
f.write(super(type(parser), parser).format_help())
logger.info("Argparse generated: %s", doc_path.relative_to(ROOT_DIR))
if __name__ == "__main__":
on_startup("build", False)
-240
View File
@@ -1,240 +0,0 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import itertools
import logging
from dataclasses import dataclass
from functools import cached_property
from pathlib import Path
from typing import Literal
import regex as re
logger = logging.getLogger("mkdocs")
ROOT_DIR = Path(__file__).parent.parent.parent.parent
ROOT_DIR_RELATIVE = "../../../../.."
EXAMPLE_DIR = ROOT_DIR / "examples"
EXAMPLE_DOC_DIR = ROOT_DIR / "docs/examples"
def title(text: str) -> str:
# Default title case
text = text.replace("_", " ").replace("/", " - ").title()
# Custom substitutions
subs = {
"io": "IO",
"rl": "RL",
"api(s?)": r"API\1",
"cli": "CLI",
"cpu": "CPU",
"ipc": "IPC",
"llm": "LLM",
"mae": "MAE",
"ner": "NER",
"tpu": "TPU",
"lora": "LoRA",
"nccl": "NCCL",
"rlhf": "RLHF",
"vllm": "vLLM",
"openai": "OpenAI",
"lmcache": "LMCache",
"multilora": "MultiLoRA",
"mlpspeculator": "MLPSpeculator",
r"fp\d+": lambda x: x.group(0).upper(), # e.g. fp16, fp32
r"int\d+": lambda x: x.group(0).upper(), # e.g. int8, int16
}
for pattern, repl in subs.items():
text = re.sub(rf"\b{pattern}\b", repl, text, flags=re.IGNORECASE)
return text
@dataclass
class Example:
"""
Example class for generating documentation content from a given path.
Attributes:
path (Path): The path to the main directory or file.
category (str): The category of the document.
Properties::
main_file() -> Path | None: Determines the main file in the given path.
other_files() -> list[Path]: Determines other files in the directory excluding
the main file.
title() -> str: Determines the title of the document.
Methods:
generate() -> str: Generates the documentation content.
"""
path: Path
category: str
@cached_property
def main_file(self) -> Path | None:
"""Determines the main file in the given path.
If path is a file, it returns the path itself. If path is a directory, it
searches for Markdown files (*.md) in the directory and returns the first one
found. If no Markdown files are found, it returns None."""
# Single file example
if self.path.is_file():
return self.path
# Multi file example with a README
if md_paths := list(self.path.glob("*.md")):
return md_paths[0]
# Multi file example without a README
return None
@cached_property
def other_files(self) -> list[Path]:
"""Determine other files in the directory excluding the main file.
If path is a file, it returns an empty list. Otherwise, it returns every file
in the directory except the main file in a list."""
# Single file example
if self.path.is_file():
return []
# Multi file example
is_other_file = lambda file: file.is_file() and file != self.main_file
return sorted(file for file in self.path.rglob("*") if is_other_file(file))
@cached_property
def is_code(self) -> bool:
return self.main_file is not None and self.main_file.suffix != ".md"
@cached_property
def title(self) -> str:
# Generate title from filename if no main md file found
if self.main_file is None or self.is_code:
return title(self.path.stem)
# Specify encoding for building on Windows
with open(self.main_file, encoding="utf-8") as f:
first_line = f.readline().strip()
match = re.match(r"^#\s+(?P<title>.+)$", first_line)
if match:
return match.group("title")
raise ValueError(f"Title not found in {self.main_file}")
def fix_relative_links(self, content: str) -> str:
"""
Fix relative links in markdown content by converting them to gh-file
format.
Args:
content (str): The markdown content to process
Returns:
str: Content with relative links converted to gh-file format
"""
# Regex to match markdown links [text](relative_path)
# This matches links that don't start with http, https, ftp, or #
link_pattern = r"\[([^\]]*)\]\((?!(?:https?|ftp)://|#)([^)]+)\)"
def replace_link(match):
link_text = match.group(1)
relative_path = match.group(2)
# Make relative to repo root
gh_file = (self.main_file.parent / relative_path).resolve()
gh_file = gh_file.relative_to(ROOT_DIR)
# Make GitHub URL
url = "https://github.com/vllm-project/vllm/"
url += "tree/main" if self.path.is_dir() else "blob/main"
gh_url = f"{url}/{gh_file}"
return f"[{link_text}]({gh_url})"
return re.sub(link_pattern, replace_link, content)
def generate(self) -> str:
content = f"# {self.title}\n\n"
url = "https://github.com/vllm-project/vllm/"
url += "tree/main" if self.path.is_dir() else "blob/main"
content += f"Source <{url}/{self.path.relative_to(ROOT_DIR)}>.\n\n"
# Use long code fence to avoid issues with
# included files containing code fences too
code_fence = "``````"
if self.main_file is not None:
# Single file example or multi file example with a README
if self.is_code:
content += (
f"{code_fence}{self.main_file.suffix[1:]}\n"
f'--8<-- "{self.main_file}"\n'
f"{code_fence}\n"
)
else:
with open(self.main_file, encoding="utf-8") as f:
# Skip the title from md snippets as it's been included above
main_content = f.readlines()[1:]
content += self.fix_relative_links("".join(main_content))
content += "\n"
else:
# Multi file example without a README
for file in self.other_files:
file_title = title(str(file.relative_to(self.path).with_suffix("")))
content += f"## {file_title}\n\n"
content += (
f'{code_fence}{file.suffix[1:]}\n--8<-- "{file}"\n{code_fence}\n\n'
)
return content
if not self.other_files:
return content
content += "## Example materials\n\n"
for file in self.other_files:
content += f'??? abstract "{file.relative_to(self.path)}"\n'
if file.suffix != ".md":
content += f" {code_fence}{file.suffix[1:]}\n"
content += f' --8<-- "{file}"\n'
if file.suffix != ".md":
content += f" {code_fence}\n"
return content
def on_startup(command: Literal["build", "gh-deploy", "serve"], dirty: bool):
# Monkey-patch dirname_to_title in awesome-nav so that sub-directory names are
# title-cased (e.g. "Offline Inference" instead of "Offline inference").
import mkdocs_awesome_nav.nav.directory as _nav_dir
_nav_dir.dirname_to_title = title
logger.info("Generating example documentation")
logger.debug("Root directory: %s", ROOT_DIR.resolve())
logger.debug("Example directory: %s", EXAMPLE_DIR.resolve())
logger.debug("Example document directory: %s", EXAMPLE_DOC_DIR.resolve())
# Create the EXAMPLE_DOC_DIR if it doesn't exist
if not EXAMPLE_DOC_DIR.exists():
EXAMPLE_DOC_DIR.mkdir(parents=True)
categories = sorted(p for p in EXAMPLE_DIR.iterdir() if p.is_dir())
examples = []
glob_patterns = ["*.py", "*.md", "*.sh"]
# Find categorised examples
for category in categories:
logger.info("Processing category: %s", category.stem)
globs = [category.glob(pattern) for pattern in glob_patterns]
for path in itertools.chain(*globs):
examples.append(Example(path, category.stem))
# Find examples in subdirectories
globs = [category.glob(f"*/{pattern}") for pattern in glob_patterns]
for path in itertools.chain(*globs):
examples.append(Example(path.parent, category.stem))
# Generate the example documentation
for example in sorted(examples, key=lambda e: e.path.stem):
example_name = f"{example.path.stem}.md"
doc_path = EXAMPLE_DOC_DIR / example.category / example_name
if not doc_path.parent.exists():
doc_path.parent.mkdir(parents=True)
# Specify encoding for building on Windows
with open(doc_path, "w+", encoding="utf-8") as f:
f.write(example.generate())
logger.debug("Example generated: %s", doc_path.relative_to(ROOT_DIR))
logger.info("Total examples generated: %d", len(examples))
-150
View File
@@ -1,150 +0,0 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import ast
import logging
from pathlib import Path
from typing import Literal
logger = logging.getLogger("mkdocs")
ROOT_DIR = Path(__file__).parent.parent.parent.parent
DOCS_DIR = ROOT_DIR / "docs"
GENERATED_METRICS_DIR = DOCS_DIR / "generated" / "metrics"
# Files to scan for metric definitions - each will generate a separate table
METRIC_SOURCE_FILES = [
{"path": "vllm/v1/metrics/loggers.py", "output": "general.inc.md"},
{
"path": "vllm/v1/spec_decode/metrics.py",
"output": "spec_decode.inc.md",
},
{
"path": "vllm/distributed/kv_transfer/kv_connector/v1/nixl/stats.py",
"output": "nixl_connector.inc.md",
},
{"path": "vllm/v1/metrics/perf.py", "output": "perf.inc.md"},
]
class MetricExtractor(ast.NodeVisitor):
"""AST visitor to extract metric definitions."""
def __init__(self):
self.metrics: list[dict[str, str]] = []
def visit_Call(self, node: ast.Call) -> None:
"""Visit function calls to find metric class instantiations."""
metric_type = self._get_metric_type(node)
if metric_type:
name = self._extract_kwarg(node, "name")
documentation = self._extract_kwarg(node, "documentation")
if name:
self.metrics.append(
{
"name": name,
"type": metric_type,
"documentation": documentation or "",
}
)
self.generic_visit(node)
def _get_metric_type(self, node: ast.Call) -> str | None:
"""Determine if this call creates a metric and return its type."""
metric_type_map = {
"_gauge_cls": "gauge",
"_counter_cls": "counter",
"_histogram_cls": "histogram",
}
if isinstance(node.func, ast.Attribute):
return metric_type_map.get(node.func.attr)
return None
def _extract_kwarg(self, node: ast.Call, key: str) -> str | None:
"""Extract a keyword argument value from a function call."""
for keyword in node.keywords:
if keyword.arg == key:
return self._get_string_value(keyword.value)
return None
def _get_string_value(self, node: ast.AST) -> str | None:
"""Extract string value from an AST node."""
if isinstance(node, ast.Constant):
return str(node.value) if node.value is not None else None
return None
def extract_metrics_from_file(filepath: Path) -> list[dict[str, str]]:
"""Parse a Python file and extract all metric definitions."""
try:
with open(filepath, encoding="utf-8") as f:
source = f.read()
tree = ast.parse(source, filename=str(filepath))
extractor = MetricExtractor()
extractor.visit(tree)
return extractor.metrics
except Exception as e:
raise RuntimeError(f"Failed to parse {filepath}: {e}") from e
def generate_markdown_table(metrics: list[dict[str, str]]) -> str:
"""Generate a markdown table from extracted metrics."""
if not metrics:
return "No metrics found.\n"
# Sort by type, then by name
metrics_sorted = sorted(metrics, key=lambda m: (m["type"], m["name"]))
lines = []
lines.append("| Metric Name | Type | Description |")
lines.append("|-------------|------|-------------|")
for metric in metrics_sorted:
name = metric["name"]
metric_type = metric["type"].capitalize()
doc = metric["documentation"].replace("\n", " ").strip()
lines.append(f"| `{name}` | {metric_type} | {doc} |")
return "\n".join(lines) + "\n"
def on_startup(command: Literal["build", "gh-deploy", "serve"], dirty: bool):
"""Generate metrics documentation tables from source files."""
logger.info("Generating metrics documentation")
# Create generated directory if it doesn't exist
GENERATED_METRICS_DIR.mkdir(parents=True, exist_ok=True)
total_metrics = 0
for source_config in METRIC_SOURCE_FILES:
source_path = source_config["path"]
output_file = source_config["output"]
filepath = ROOT_DIR / source_path
if not filepath.exists():
raise FileNotFoundError(f"Metrics source file not found: {filepath}")
logger.debug("Extracting metrics from: %s", source_path)
metrics = extract_metrics_from_file(filepath)
logger.debug("Found %d metrics in %s", len(metrics), source_path)
# Generate and write the markdown table for this source
table_content = generate_markdown_table(metrics)
output_path = GENERATED_METRICS_DIR / output_file
with open(output_path, "w", encoding="utf-8") as f:
f.write(table_content)
total_metrics += len(metrics)
logger.info(
"Generated metrics table: %s (%d metrics)",
output_path.relative_to(ROOT_DIR),
len(metrics),
)
logger.info(
"Total metrics generated: %d across %d files",
total_metrics,
len(METRIC_SOURCE_FILES),
)
+39 -4
View File
@@ -19,6 +19,7 @@ The on_page_markdown hook passes the current page context to the preprocessor be
each page is converted.
"""
import posixpath
from pathlib import Path
import regex as re
@@ -38,18 +39,22 @@ TITLE = r"(?P<title>[^\[\]<>]+?)"
REPO = r"(?P<repo>.+?/.+?)"
TYPE = r"(?P<type>issues|pull|projects)"
NUMBER = r"(?P<number>\d+)"
VERSION = r"[^/\s]+"
PATH = r"(?P<path>[^\s]+?)"
FRAGMENT = r"(?P<fragment>#[^\s]+)?"
URL = f"https://github.com/{REPO}/{TYPE}/{NUMBER}{FRAGMENT}"
URL_GITHUB = f"https://github.com/{REPO}/{TYPE}/{NUMBER}{FRAGMENT}"
RELATIVE = rf"(?!(https?|ftp)://|#){PATH}{FRAGMENT}"
URL_DOCS = f"https://docs.vllm.ai/en/{VERSION}/{PATH}{FRAGMENT}"
# Common titles to use for GitHub links when none is provided in the link.
TITLES = {"issues": "Issue ", "pull": "Pull Request ", "projects": "Project "}
# Regex to match GitHub issue, PR, and project links with optional titles.
github_link = re.compile(rf"(\[{TITLE}\]\(|<){URL}(\)|>)")
github_link = re.compile(rf"(\[{TITLE}\]\(|<){URL_GITHUB}(\)|>)")
# Regex to match relative file links with optional titles.
relative_link = re.compile(rf"\[{TITLE}\]\({RELATIVE}\)")
# Regex to match absolute docs.vllm.ai links (should only exist in CLI).
docs_link = re.compile(rf"\[{TITLE}\]\({URL_DOCS}\)")
class UrlSchemesPreprocessor(Preprocessor):
@@ -61,7 +66,8 @@ class UrlSchemesPreprocessor(Preprocessor):
def run(self, lines):
page = self.ext.page
if page is None or getattr(page.file, "abs_src_path", None) is None:
files = self.ext.files
if page is None:
return lines
def replace_relative_link(match: re.Match) -> str:
@@ -70,7 +76,7 @@ class UrlSchemesPreprocessor(Preprocessor):
"""
title = match.group("title")
path = match.group("path")
path = (Path(page.file.abs_src_path).parent / path).resolve()
path = ((DOC_DIR / page.file.src_uri).parent / path).resolve()
fragment = match.group("fragment") or ""
# Check if the path exists and is outside the docs dir
@@ -105,9 +111,36 @@ class UrlSchemesPreprocessor(Preprocessor):
url = f"https://github.com/{repo}/{type}/{number}{fragment}"
return f"[{gh_icon} {title}]({url})"
def replace_docs_link(match: re.Match) -> str:
"""Rewrite absolute docs.vllm.ai links as doc-relative links."""
title = match.group("title")
path = match.group("path").rstrip("/")
fragment = match.group("fragment") or ""
# vllm.config.<Class> API reference -> mkdocstrings cross-reference
if path == "api/vllm/config" and re.fullmatch(
r"#vllm\.config\.\w+", fragment
):
ident = fragment[1:]
return f"[`{ident}`][{ident}]"
# Other docs pages -> link relative to the current page, but only
# when the target is a known docs page (real or generated); leave
# unknown/external URLs untouched. This is correct even when the same
# docstring is also rendered on its API reference page.
src = f"{path.removesuffix('.html')}.md"
if files.get_file_from_path(src) is None:
return match.group(0)
rel = posixpath.relpath(src, posixpath.dirname(page.file.src_uri))
# Auto-wrapped bare URLs use the URL as their title; make it readable.
if title.startswith("http"):
title = path.removesuffix(".html")
return f"[{title}]({rel}{fragment})"
markdown = "\n".join(lines)
markdown = github_link.sub(replace_github_link, markdown)
markdown = relative_link.sub(replace_relative_link, markdown)
markdown = docs_link.sub(replace_docs_link, markdown)
return markdown.split("\n")
@@ -116,6 +149,7 @@ class UrlSchemesExtension(Extension):
def __init__(self, **kwargs):
self.page = None
self.files = None
super().__init__(**kwargs)
def extendMarkdown(self, md):
@@ -138,4 +172,5 @@ def on_page_markdown(
) -> str:
"""Pass the current page context to the preprocessor."""
_ext.page = page
_ext.files = files
return markdown