WEBDIENSTE/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-08-23 08:02:23 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs: handle more links (#3434)

Browse Source
This commit is contained in:
Eugene Yurtsev
2025-02-13 23:43:29 +00:00
committed by GitHub
parent 3e1bbd3123
commit 437891aa4f
2 changed files with 81 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/_scripts/notebook_convert.py
+62 -53
View File
@@ -64,6 +64,67 @@ def _rewrite_cell_magic(code: str) -> str:
return "\n".join(rewritten_lines)
def _convert_links_in_markdown(markdown: str) -> str:
"""Convert links present in notebook markdown cells to standardized format.
We want to update markdown links code cells by linking to markdown
files rather than assuming that the link is to the finalized HTML.
This code is needed temporarily since the markdown links that are present
in ipython notebooks do not follow the same conventions as regular markdown
files in mkdocs (which should link to a .md file).
"""
# Define the regex pattern in parts for clarity:
pattern = (
r"(?<!!)" # Negative lookbehind: ensure the link is not an image (i.e., doesn't start with "!")
r"\[" # Literal '[' indicating the start of the link text.
r"(?P<text>[^\]]*)" # Named group 'text': match any characters except ']', representing the link text.
r"\]" # Literal ']' indicating the end of the link text.
r"\(" # Literal '(' indicating the start of the URL.
r"(?![^\)]*//)" # Negative lookahead: ensure that the URL does not contain '//' (skip absolute URLs).
r"(?P<url>[^)]*)" # Named group 'url': match any characters except ')', representing the URL.
r"\)" # Literal ')' indicating the end of the URL.
)
def custom_replacement(match):
"""logic will correct the link format used in ipython notebooks
Ipython notebooks were being converted directly into HTML links
instead of markdown links that retain the markdown extension.
It needs to handle the following cases:
- optional fragments (e.g., `#section`)
e.g., `[text](url/#section)` -> `[text](url.md#section)`
e.g., `[text](url#section)` -> `[text](url.md#section)`
- relative paths (e.g., `../path/to/file`) need to be denested by 1 level
"""
text = match.group("text")
url = match.group("url")
if url.startswith("../"):
# we strip the "../" from the start of the URL
# We only need to denest one level.
url = url[3:]
url = url.rstrip("/") # Strip `/` from the end of the URL
# if url has a fragment
if "#" in url:
url, fragment = url.split("#")
url = url.rstrip("/")
# Strip `/` from the end of the URL
return f"[{text}]({url}.md#{fragment})"
# Otherwise add the .md extension
return f"[{text}]({url}.md)"
return re.sub(
pattern,
custom_replacement,
markdown,
)
class EscapePreprocessor(Preprocessor):
def __init__(self, markdown_exec_migration: bool = False, **kwargs) -> None:
super().__init__(**kwargs)
@@ -79,59 +140,7 @@ class EscapePreprocessor(Preprocessor):
cell.source,
)
else:
# We want to update markdown links in cell.source by replacing a '.ipynb'
# extension with '.md', but only for links that:
# - are not image links (i.e. not preceded by '!')
# - do not contain '//' in the URL (to avoid external links)
# Define the regex pattern in parts for clarity:
pattern = (
r"(?<!!)" # Negative lookbehind: ensure the link is not an image (i.e., doesn't start with "!")
r"\[" # Literal '[' indicating the start of the link text.
r"(?P<text>[^\]]*)" # Named group 'text': match any characters except ']', representing the link text.
r"\]" # Literal ']' indicating the end of the link text.
r"\(" # Literal '(' indicating the start of the URL.
r"(?![^\)]*//)" # Negative lookahead: ensure that the URL does not contain '//' (skip absolute URLs).
r"(?P<url>[^)]*)" # Named group 'url': match any characters except ')', representing the URL.
r"\)" # Literal ')' indicating the end of the URL.
)
def custom_replacement(match):
"""logic will correct the link format used in ipython notebooks
Ipython notebooks were being converted directly into HTML links
instead of markdown links that retain the markdown extension.
It needs to handle the following cases:
- optional fragments (e.g., `#section`)
e.g., `[text](url/#section)` -> `[text](url.md#section)`
e.g., `[text](url#section)` -> `[text](url.md#section)`
- relative paths (e.g., `../path/to/file`) need to be
denested by 1 level
"""
text = match.group("text")
url = match.group("url")
if url.startswith("../"):
# we strip the "../" from the start of the URL
# We only need to denest one level.
url = url[3:]
url = url.rstrip("/") # Strip `/` from the end of the URL
# if url has a fragment
if "#" in url:
url, fragment = url.split("#")
# Strip `/` from the end of the URL
return f"[{text}]({url}.md#{fragment})"
# Otherwise add the .md extension
return f"[{text}]({url}.md)"
cell.source = re.sub(
pattern,
custom_replacement,
cell.source,
)
cell.source = _convert_links_in_markdown(cell.source)
# Fix image paths in <img> tags
cell.source = re.sub(
docs/tests/unit_tests/test_notebook_conversion.py
+19 -1
View File
@@ -1,6 +1,7 @@
import nbformat
from _scripts.notebook_convert import md_executable
from _scripts.notebook_convert import md_executable, _convert_links_in_markdown
import pytest
EXPECTED_OUTPUT = """\
@@ -56,3 +57,20 @@ def test_convert_input_cell() -> None:
notebook.cells.append(nbformat.v4.new_code_cell(STDIN_INPUT))
markdown, _ = md_executable.from_notebook_node(notebook)
assert markdown == STDIN_OUTPUT
@pytest.mark.parametrize(
"source, expected",
[
(
"This is a [link](https://example.com).",
"This is a [link](https://example.com).",
),
("This is a [link](../foo).", "This is a [link](foo.md)."),
("This is a [link](../foo#hello).", "This is a [link](foo.md#hello)."),
("This is a [link](../foo/#hello).", "This is a [link](foo.md#hello)."),
],
)
def test_link_conversion(source: str, expected: str) -> None:
"""Test logic to convert links in markdown cells."""
assert _convert_links_in_markdown(source) == expected