244 lines
10 KiB
Python
244 lines
10 KiB
Python
"""
|
|
FILE: app/core/chunking/chunking_parser.py
|
|
DESCRIPTION: Zerlegt Markdown in logische Einheiten (RawBlocks).
|
|
Hält alle Überschriftenebenen (H1-H6) im Stream.
|
|
Stellt die Funktion parse_edges_robust zur Verfügung.
|
|
WP-24c v4.2.0: Identifiziert Edge-Zonen und markiert sie für Chunking-Ausschluss.
|
|
WP-24c v4.2.5: Callout-Exclusion - Callouts werden als separate RawBlocks identifiziert und ausgeschlossen.
|
|
"""
|
|
import re
|
|
import os
|
|
from typing import List, Tuple, Set, Dict, Any, Optional
|
|
from .chunking_models import RawBlock
|
|
from .chunking_utils import extract_frontmatter_from_text
|
|
|
|
_WS = re.compile(r'\s+')
|
|
_SENT_SPLIT = re.compile(r'(?<=[.!?])\s+(?=[A-ZÄÖÜ0-9„(])')
|
|
|
|
def split_sentences(text: str) -> list[str]:
|
|
"""Teilt Text in Sätze auf unter Berücksichtigung deutscher Interpunktion."""
|
|
text = _WS.sub(' ', text.strip())
|
|
if not text: return []
|
|
# Splittet bei Punkt, Ausrufezeichen oder Fragezeichen, gefolgt von Leerzeichen und Großbuchstabe
|
|
return [p.strip() for p in _SENT_SPLIT.split(text) if p.strip()]
|
|
|
|
def parse_blocks(md_text: str) -> Tuple[List[RawBlock], str]:
|
|
"""
|
|
Zerlegt Text in logische Einheiten (RawBlocks), inklusive H1-H6.
|
|
WP-24c v4.2.0: Identifiziert Edge-Zonen (LLM-Validierung & Note-Scope) und markiert sie für Chunking-Ausschluss.
|
|
WP-24c v4.2.6: Callouts werden mit is_meta_content=True markiert (werden gechunkt, aber später entfernt).
|
|
"""
|
|
blocks = []
|
|
h1_title = "Dokument"
|
|
section_path = "/"
|
|
current_section_title = None
|
|
|
|
# Frontmatter entfernen
|
|
fm, text_without_fm = extract_frontmatter_from_text(md_text)
|
|
|
|
# WP-24c v4.2.0: Konfigurierbare Header-Namen und -Ebenen
|
|
llm_validation_headers = os.getenv(
|
|
"MINDNET_LLM_VALIDATION_HEADERS",
|
|
"Unzugeordnete Kanten,Edge Pool,Candidates"
|
|
)
|
|
llm_validation_header_list = [h.strip() for h in llm_validation_headers.split(",") if h.strip()]
|
|
if not llm_validation_header_list:
|
|
llm_validation_header_list = ["Unzugeordnete Kanten", "Edge Pool", "Candidates"]
|
|
|
|
note_scope_headers = os.getenv(
|
|
"MINDNET_NOTE_SCOPE_ZONE_HEADERS",
|
|
"Smart Edges,Relationen,Global Links,Note-Level Relations,Globale Verbindungen"
|
|
)
|
|
note_scope_header_list = [h.strip() for h in note_scope_headers.split(",") if h.strip()]
|
|
if not note_scope_header_list:
|
|
note_scope_header_list = ["Smart Edges", "Relationen", "Global Links", "Note-Level Relations", "Globale Verbindungen"]
|
|
|
|
# Header-Ebenen konfigurierbar (Default: LLM=3, Note-Scope=2)
|
|
llm_validation_level = int(os.getenv("MINDNET_LLM_VALIDATION_HEADER_LEVEL", "3"))
|
|
note_scope_level = int(os.getenv("MINDNET_NOTE_SCOPE_HEADER_LEVEL", "2"))
|
|
|
|
# Status-Tracking für Edge-Zonen
|
|
in_exclusion_zone = False
|
|
exclusion_zone_type = None # "llm_validation" oder "note_scope"
|
|
|
|
# H1 für Note-Titel extrahieren (Metadaten-Zweck)
|
|
h1_match = re.search(r'^#\s+(.*)', text_without_fm, re.MULTILINE)
|
|
if h1_match:
|
|
h1_title = h1_match.group(1).strip()
|
|
|
|
lines = text_without_fm.split('\n')
|
|
buffer = []
|
|
|
|
# WP-24c v4.2.5: Callout-Erkennung (auch verschachtelt: >>)
|
|
# Regex für Callouts: >\s*[!edge] oder >\s*[!abstract] (auch mit mehreren >)
|
|
callout_pattern = re.compile(r'^\s*>{1,}\s*\[!(edge|abstract)\]', re.IGNORECASE)
|
|
|
|
# WP-24c v4.2.5: Markiere verarbeitete Zeilen, um sie zu überspringen
|
|
processed_indices = set()
|
|
|
|
for i, line in enumerate(lines):
|
|
if i in processed_indices:
|
|
continue
|
|
|
|
stripped = line.strip()
|
|
|
|
# WP-24c v4.2.5: Callout-Erkennung (VOR Heading-Erkennung)
|
|
# Prüfe, ob diese Zeile ein Callout startet
|
|
callout_match = callout_pattern.match(line)
|
|
if callout_match:
|
|
# Vorherigen Text-Block abschließen
|
|
if buffer:
|
|
content = "\n".join(buffer).strip()
|
|
if content:
|
|
blocks.append(RawBlock(
|
|
"paragraph", content, None, section_path, current_section_title,
|
|
exclude_from_chunking=in_exclusion_zone
|
|
))
|
|
buffer = []
|
|
|
|
# Sammle alle Zeilen des Callout-Blocks
|
|
callout_lines = [line]
|
|
leading_gt_count = len(line) - len(line.lstrip('>'))
|
|
processed_indices.add(i)
|
|
|
|
# Sammle alle Zeilen, die zum Callout gehören (gleiche oder höhere Einrückung)
|
|
j = i + 1
|
|
while j < len(lines):
|
|
next_line = lines[j]
|
|
if not next_line.strip().startswith('>'):
|
|
break
|
|
next_leading_gt = len(next_line) - len(next_line.lstrip('>'))
|
|
if next_leading_gt < leading_gt_count:
|
|
break
|
|
callout_lines.append(next_line)
|
|
processed_indices.add(j)
|
|
j += 1
|
|
|
|
# WP-24c v4.2.6: Erstelle Callout-Block mit is_meta_content = True
|
|
# Callouts werden gechunkt (für Chunk-Attribution), aber später entfernt (Clean-Context)
|
|
callout_content = "\n".join(callout_lines)
|
|
blocks.append(RawBlock(
|
|
"callout", callout_content, None, section_path, current_section_title,
|
|
exclude_from_chunking=in_exclusion_zone, # Nur Edge-Zonen werden ausgeschlossen
|
|
is_meta_content=True # WP-24c v4.2.6: Markierung für spätere Entfernung
|
|
))
|
|
continue
|
|
|
|
# Heading-Erkennung (H1 bis H6)
|
|
heading_match = re.match(r'^(#{1,6})\s+(.*)', stripped)
|
|
if heading_match:
|
|
# Vorherigen Text-Block abschließen
|
|
if buffer:
|
|
content = "\n".join(buffer).strip()
|
|
if content:
|
|
blocks.append(RawBlock(
|
|
"paragraph", content, None, section_path, current_section_title,
|
|
exclude_from_chunking=in_exclusion_zone
|
|
))
|
|
buffer = []
|
|
|
|
level = len(heading_match.group(1))
|
|
title = heading_match.group(2).strip()
|
|
|
|
# WP-24c v4.2.0: Prüfe, ob dieser Header eine Edge-Zone startet
|
|
is_llm_validation_zone = (
|
|
level == llm_validation_level and
|
|
any(title.lower() == h.lower() for h in llm_validation_header_list)
|
|
)
|
|
is_note_scope_zone = (
|
|
level == note_scope_level and
|
|
any(title.lower() == h.lower() for h in note_scope_header_list)
|
|
)
|
|
|
|
if is_llm_validation_zone:
|
|
in_exclusion_zone = True
|
|
exclusion_zone_type = "llm_validation"
|
|
elif is_note_scope_zone:
|
|
in_exclusion_zone = True
|
|
exclusion_zone_type = "note_scope"
|
|
elif in_exclusion_zone:
|
|
# Neuer Header gefunden, der keine Edge-Zone ist -> Zone beendet
|
|
in_exclusion_zone = False
|
|
exclusion_zone_type = None
|
|
|
|
# Pfad- und Titel-Update für die Metadaten der folgenden Blöcke
|
|
if level == 1:
|
|
current_section_title = title; section_path = "/"
|
|
elif level == 2:
|
|
current_section_title = title; section_path = f"/{current_section_title}"
|
|
|
|
# Die Überschrift selbst als regulären Block hinzufügen (auch markiert, wenn in Zone)
|
|
blocks.append(RawBlock(
|
|
"heading", stripped, level, section_path, current_section_title,
|
|
exclude_from_chunking=in_exclusion_zone
|
|
))
|
|
continue
|
|
|
|
# Trenner (---) oder Leerzeilen beenden Blöcke, außer innerhalb von Callouts
|
|
if (not stripped or stripped == "---") and not line.startswith('>'):
|
|
if buffer:
|
|
content = "\n".join(buffer).strip()
|
|
if content:
|
|
blocks.append(RawBlock(
|
|
"paragraph", content, None, section_path, current_section_title,
|
|
exclude_from_chunking=in_exclusion_zone
|
|
))
|
|
buffer = []
|
|
if stripped == "---":
|
|
blocks.append(RawBlock(
|
|
"separator", "---", None, section_path, current_section_title,
|
|
exclude_from_chunking=in_exclusion_zone
|
|
))
|
|
else:
|
|
buffer.append(line)
|
|
|
|
if buffer:
|
|
content = "\n".join(buffer).strip()
|
|
if content:
|
|
blocks.append(RawBlock(
|
|
"paragraph", content, None, section_path, current_section_title,
|
|
exclude_from_chunking=in_exclusion_zone
|
|
))
|
|
|
|
return blocks, h1_title
|
|
|
|
def parse_edges_robust(text: str) -> List[Dict[str, Any]]:
|
|
"""
|
|
Extrahiert Kanten-Kandidaten aus Wikilinks und Callouts.
|
|
WP-24c v4.2.7: Gibt Liste von Dicts zurück mit is_callout Flag für Chunk-Attribution.
|
|
|
|
Returns:
|
|
List[Dict] mit keys: "edge" (str: "kind:target"), "is_callout" (bool)
|
|
"""
|
|
found_edges: List[Dict[str, any]] = []
|
|
# 1. Wikilinks [[rel:kind|target]]
|
|
inlines = re.findall(r'\[\[rel:([^\|\]]+)\|?([^\]]*)\]\]', text)
|
|
for kind, target in inlines:
|
|
k = kind.strip().lower()
|
|
t = target.strip()
|
|
if k and t:
|
|
found_edges.append({"edge": f"{k}:{t}", "is_callout": False})
|
|
|
|
# 2. Callout Edges > [!edge] kind
|
|
lines = text.split('\n')
|
|
current_edge_type = None
|
|
for line in lines:
|
|
stripped = line.strip()
|
|
callout_match = re.match(r'>\s*\[!edge\]\s*([^:\s]+)', stripped)
|
|
if callout_match:
|
|
current_edge_type = callout_match.group(1).strip().lower()
|
|
# Links in der gleichen Zeile des Callouts
|
|
links = re.findall(r'\[\[([^\]]+)\]\]', stripped)
|
|
for l in links:
|
|
if "rel:" not in l:
|
|
found_edges.append({"edge": f"{current_edge_type}:{l}", "is_callout": True})
|
|
continue
|
|
# Links in Folgezeilen des Callouts
|
|
if current_edge_type and stripped.startswith('>'):
|
|
links = re.findall(r'\[\[([^\]]+)\]\]', stripped)
|
|
for l in links:
|
|
if "rel:" not in l:
|
|
found_edges.append({"edge": f"{current_edge_type}:{l}", "is_callout": True})
|
|
elif not stripped.startswith('>'):
|
|
current_edge_type = None
|
|
return found_edges |