From 78b6c6f45904a50a3c475c376f8202c64f5c795d Mon Sep 17 00:00:00 2001
From: ankraft <an.kraft@gmail.com>
Date: Fri, 26 Apr 2024 12:44:03 +0200
Subject: [PATCH] Detecting images and tables in the markdown parser
---
toMkdocs/toMkdocs.py | 39 +++++++++++++++++++++++++++++++++++++--
1 file changed, 37 insertions(+), 2 deletions(-)
diff --git a/toMkdocs/toMkdocs.py b/toMkdocs/toMkdocs.py
index aaace80..9277e2b 100644
--- a/toMkdocs/toMkdocs.py
+++ b/toMkdocs/toMkdocs.py
@@ -24,6 +24,11 @@ class LineType(Enum):
CODEFENCEEND = auto()
LIST = auto()
NOTE = auto()
+ STANDALONEIMAGE = auto()
+ TABLEHEADER = auto()
+ TABLESEPARATOR = auto()
+ TABLEROW = auto()
+ TABLELASTROW = auto()
@dataclass
@@ -136,6 +141,9 @@ _matchHeaderNumber = re.compile(r'\b[A-Za-z0-9]\d*(\.\d+)*\b', re.IGNORECASE)
_matchCodefenceStart = re.compile(r'\s*```\s?.*', re.IGNORECASE)
_matchCodefenceEnd = re.compile(r'\s*```\s?', re.IGNORECASE)
_matchNote = re.compile(r'^\s*>\s*', re.IGNORECASE)
+_matchStandAloneImage = re.compile(r'^\s*!\[[^\]]*\]\(([^)]*)\)\s*', re.IGNORECASE)
+_matchTable = re.compile(r'^\s*\|.*\|\s$', re.IGNORECASE)
+_matchTableSeparator = re.compile(r'^\s*\|([-: ]+\|)+\s*$', re.IGNORECASE)
_match2spaceListIndention = re.compile(r'^\s{2}-', re.IGNORECASE)
_markdownLink = re.compile(r'[^!]\[[^\]]*\]\((#[^)]*)\)', re.IGNORECASE)
_htmlLink = re.compile(r'<a\s+href="([^"\']*)">[^<]*</a>', re.IGNORECASE)
@@ -186,6 +194,8 @@ def analyseMarkdown(filename:str) -> list[Clause]:
# Go through the lines and detect headers and codefences
inCodefence = False
+ inTable = False
+ tableHasSeparator = False
for line in inLines:
# Detect and handle codefences
@@ -204,13 +214,38 @@ def analyseMarkdown(filename:str) -> list[Clause]:
if inCodefence:
outClauses[-1].append(Line(line, LineType.CODE))
continue
-
+
+ # Detect and handle tables
+ if _matchTable.match(line) and not inTable:
+ inTable = True
+ outClauses[-1].append(Line(line, LineType.TABLEHEADER))
+ continue
+ if inTable:
+ if _matchTableSeparator.match(line) and not tableHasSeparator:
+ outClauses[-1].append(Line(line, LineType.TABLESEPARATOR))
+ tableHasSeparator = True
+ continue
+ elif _matchTable.match(line):
+ outClauses[-1].append(Line(line, LineType.TABLEROW))
+ continue
+ else:
+ inTable = False
+ tableHasSeparator = False
+ # Mark the previous line as the last row in the table
+ outClauses[-1].lines[-1].lineType = LineType.TABLELASTROW
+ # continue with other matches
+
# Detect notes
# Notes are lines that start with a '>'.
if _matchNote.match(line):
outClauses[-1].append(Line(line, LineType.NOTE))
continue
-
+
+ # Detect images on a single line
+ if (m := _matchStandAloneImage.match(line)):
+ outClauses[-1].append(Line(line, LineType.STANDALONEIMAGE))
+ continue
+
# Detect headers
_lineType = LineType.TEXT
if (m := _matchHeader.match(line)):
--
GitLab