feat(embedding): add NIST/ENISA/standard section numbering to chunker

Extends _LEGAL_SECTION_RE to detect:
- Numbered sections: 1.1 Title, 2.3.1 Subtitle
- Control family IDs: AC-1, AU-2, PO.1, PW.1.1
- Table/Figure/Appendix references
Also adds EUR-Lex HTML replacement script.

58 embedding-service tests passing.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

embedding-service/main.py

@@ -281,7 +281,7 @@ ENGLISH_ABBREVIATIONS = {
 # Combined abbreviations for both languages
 ALL_ABBREVIATIONS = GERMAN_ABBREVIATIONS | ENGLISH_ABBREVIATIONS
 
-# Regex pattern for legal section headers (§, Art., Article, Section, etc.)
+# Regex pattern for legal/standard section headers
 _LEGAL_SECTION_RE = re.compile(
     r'^(?:'
     r'§\s*\d+'                          # § 25, § 5a
@@ -296,6 +296,12 @@ _LEGAL_SECTION_RE = re.compile(
     r'|Part\s+[IVXLC\d]+'              # Part III
     r'|Recital\s+\d+'                   # Recital 42
     r'|Erwaegungsgrund\s+\d+'           # Erwaegungsgrund 26
+    # NIST/ENISA/standard numbering
+    r'|\d+\.\d+(?:\.\d+)*\s+[A-ZÄÖÜ]'  # 1.1 Title, 2.3.1 Subtitle
+    r'|[A-Z]{2,4}[-\.]\d+(?:\.\d+)*\b'  # AC-1, AU-2, PO.1, PW.1.1
+    r'|Table\s+\d+'                      # Table 1, Table A-1
+    r'|Figure\s+\d+'                     # Figure 1
+    r'|Appendix\s+[A-Z\d]'              # Appendix A, Appendix 1
     r')',
     re.IGNORECASE | re.MULTILINE
 )