From 633ad636ef5fdec08b60e154aa84c0f15f42e759 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?H=C3=A5kon=20H=C3=A6gland?= <hakon.hagland@gmail.com>
Date: Thu, 6 Jun 2024 17:34:32 +0200
Subject: [PATCH] Use more precise regex

Use more precise regex in set-keyword-status script
---
 scripts/python/src/fodt/add_keyword.py        | 4 ++--
 scripts/python/src/fodt/add_keyword_status.py | 4 ++--
 scripts/python/src/fodt/constants.py          | 3 +++
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/scripts/python/src/fodt/add_keyword.py b/scripts/python/src/fodt/add_keyword.py
index 69847889..708a7908 100644
--- a/scripts/python/src/fodt/add_keyword.py
+++ b/scripts/python/src/fodt/add_keyword.py
@@ -11,7 +11,7 @@
 
 import click
 
-from fodt.constants import ClickOptions, Directories, FileExtensions, KeywordStatus
+from fodt.constants import ClickOptions, Directories, FileExtensions, KeywordStatus, Regex
 from fodt.create_subdocument import CreateSubDocument3
 from fodt.helpers import Helpers
 from fodt.remove_subsections import RemoveSubSections
@@ -118,7 +118,7 @@ def extract_keyword_name(self, href: str) -> str:
         # Assume href starts with "#xxx.yyy.zzz.KEYWORD_NAME<space>"
         # or "#xxx.yyy.zzz.KEYWORD_NAME|outline"
         # KEYWORD_NAME can contain letters, numbers, and optionally a trailing hyphen or en-dash
-        if m:= re.match(r"#\d+\.\d+\.\d+\.(\w+[\-–]?)(?:\s+|$|\|outline$)", href):
+        if m:= re.match(Regex.href_keyword_name, href):
             return m.group(1)
         else:
             return '<NOT FOUND>'
diff --git a/scripts/python/src/fodt/add_keyword_status.py b/scripts/python/src/fodt/add_keyword_status.py
index ab477056..39002032 100644
--- a/scripts/python/src/fodt/add_keyword_status.py
+++ b/scripts/python/src/fodt/add_keyword_status.py
@@ -17,7 +17,7 @@
 
 import click
 
-from fodt.constants import ClickOptions, Directories, FileExtensions, KeywordStatus
+from fodt.constants import ClickOptions, Directories, FileExtensions, KeywordStatus, Regex
 from fodt.xml_helpers import XMLHelper
 
 class AppendixKeywordHandler(xml.sax.handler.ContentHandler):
@@ -132,7 +132,7 @@ def handle_table_row(
                 href = attrs.getValue("xlink:href")
                 # the href value is on the form "#1.2.1.ACTDIMS – ACTION Keyword Dimensions"
                 # we want to extract the keyword name from this string
-                if match := re.match(r"#\d+.\d+.\d+.(\w+)\s+", href):
+                if match := re.match(Regex.href_keyword_name, href):
                     self.current_keyword = match.group(1)
         elif self.in_table_cell and name == 'text:p':
             if self.found_table_cell:
diff --git a/scripts/python/src/fodt/constants.py b/scripts/python/src/fodt/constants.py
index 5867498f..6b966ea6 100644
--- a/scripts/python/src/fodt/constants.py
+++ b/scripts/python/src/fodt/constants.py
@@ -76,6 +76,9 @@ class MetaSections():
         'office:master-styles',
     ]
 
+class Regex:
+    href_keyword_name = r"#\d+\.\d+\.\d+\.(\w+[\-–]?)(?:\s+|$|\|outline$)"
+
 class TagEvent():
     NONE = 0
     START = 1