Fix: Sidebar scrollable + add Eltern-Portal nav link

overflow-hidden → overflow-y-auto so all nav items are reachable. Added /parent (Eltern-Portal) link with people icon. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-25 20:49:44 +02:00
parent d87645ffce
commit 45287b3541
48 changed files with 6 additions and 1 deletions
--- a/klausur-service/backend/ocr/gutter/core.py
+++ b/klausur-service/backend/ocr/gutter/core.py
@@ -0,0 +1,275 @@
+"""
+Gutter Repair Core — spellchecker setup, data types, and single-word repair logic.
+
+Extracted from cv_gutter_repair.py for modularity.
+
+Lizenz: Apache 2.0 (kommerziell nutzbar)
+DATENSCHUTZ: Alle Verarbeitung erfolgt lokal.
+"""
+
+import itertools
+import logging
+import re
+import uuid
+from dataclasses import dataclass, field, asdict
+from typing import Any, Dict, List, Optional, Tuple
+
+logger = logging.getLogger(__name__)
+
+# ---------------------------------------------------------------------------
+# Spellchecker setup (lazy, cached)
+# ---------------------------------------------------------------------------
+
+_spell_de = None
+_spell_en = None
+_SPELL_AVAILABLE = False
+
+def _init_spellcheckers():
+    """Lazy-load DE + EN spellcheckers (cached across calls)."""
+    global _spell_de, _spell_en, _SPELL_AVAILABLE
+    if _spell_de is not None:
+        return
+    try:
+        from spellchecker import SpellChecker
+        _spell_de = SpellChecker(language='de', distance=1)
+        _spell_en = SpellChecker(language='en', distance=1)
+        _SPELL_AVAILABLE = True
+        logger.info("Gutter repair: spellcheckers loaded (DE + EN)")
+    except ImportError:
+        logger.warning("pyspellchecker not installed — gutter repair unavailable")
+
+
+def _is_known(word: str) -> bool:
+    """Check if a word is known in DE or EN dictionary."""
+    _init_spellcheckers()
+    if not _SPELL_AVAILABLE:
+        return False
+    w = word.lower()
+    return bool(_spell_de.known([w])) or bool(_spell_en.known([w]))
+
+
+def _spell_candidates(word: str, lang: str = "both") -> List[str]:
+    """Get all plausible spellchecker candidates for a word (deduplicated)."""
+    _init_spellcheckers()
+    if not _SPELL_AVAILABLE:
+        return []
+    w = word.lower()
+    seen: set = set()
+    results: List[str] = []
+
+    for checker in ([_spell_de, _spell_en] if lang == "both"
+                    else [_spell_de] if lang == "de"
+                    else [_spell_en]):
+        if checker is None:
+            continue
+        cands = checker.candidates(w)
+        if cands:
+            for c in cands:
+                if c and c != w and c not in seen:
+                    seen.add(c)
+                    results.append(c)
+
+    return results
+
+
+# ---------------------------------------------------------------------------
+# Gutter position detection
+# ---------------------------------------------------------------------------
+
+# Minimum word length for spell-fix (very short words are often legitimate)
+_MIN_WORD_LEN_SPELL = 3
+
+# Minimum word length for hyphen-join candidates (fragments at the gutter
+# can be as short as 1-2 chars, e.g. "ve" from "ver-künden")
+_MIN_WORD_LEN_HYPHEN = 2
+
+# How close to the right column edge a word must be to count as "gutter-adjacent".
+# Expressed as fraction of column width (e.g. 0.75 = rightmost 25%).
+_GUTTER_EDGE_THRESHOLD = 0.70
+
+# Small common words / abbreviations that should NOT be repaired
+_STOPWORDS = frozenset([
+    # German
+    "ab", "an", "am", "da", "er", "es", "im", "in", "ja", "ob", "so", "um",
+    "zu", "wo", "du", "eh", "ei", "je", "na", "nu", "oh",
+    # English
+    "a", "am", "an", "as", "at", "be", "by", "do", "go", "he", "if", "in",
+    "is", "it", "me", "my", "no", "of", "on", "or", "so", "to", "up", "us",
+    "we",
+])
+
+# IPA / phonetic patterns — skip these cells
+_IPA_RE = re.compile(r'[\[\]/ˈˌːʃʒθðŋɑɒæɔəɛɪʊʌ]')
+
+
+def _is_ipa_text(text: str) -> bool:
+    """True if text looks like IPA transcription."""
+    return bool(_IPA_RE.search(text))
+
+
+def _word_is_at_gutter_edge(word_bbox: Dict, col_x: float, col_width: float) -> bool:
+    """Check if a word's right edge is near the right boundary of its column."""
+    if col_width <= 0:
+        return False
+    word_right = word_bbox.get("left", 0) + word_bbox.get("width", 0)
+    col_right = col_x + col_width
+    # Word's right edge within the rightmost portion of the column
+    relative_pos = (word_right - col_x) / col_width
+    return relative_pos >= _GUTTER_EDGE_THRESHOLD
+
+
+# ---------------------------------------------------------------------------
+# Suggestion types
+# ---------------------------------------------------------------------------
+
+@dataclass
+class GutterSuggestion:
+    """A single correction suggestion."""
+    id: str = field(default_factory=lambda: str(uuid.uuid4())[:8])
+    type: str = ""             # "hyphen_join" | "spell_fix"
+    zone_index: int = 0
+    row_index: int = 0
+    col_index: int = 0
+    col_type: str = ""
+    cell_id: str = ""
+    original_text: str = ""
+    suggested_text: str = ""
+    # For hyphen_join:
+    next_row_index: int = -1
+    next_row_cell_id: str = ""
+    next_row_text: str = ""
+    missing_chars: str = ""
+    display_parts: List[str] = field(default_factory=list)
+    # Alternatives (other plausible corrections the user can pick from)
+    alternatives: List[str] = field(default_factory=list)
+    # Meta:
+    confidence: float = 0.0
+    reason: str = ""           # "gutter_truncation" | "gutter_blur" | "hyphen_continuation"
+
+    def to_dict(self) -> Dict[str, Any]:
+        return asdict(self)
+
+
+# ---------------------------------------------------------------------------
+# Core repair logic
+# ---------------------------------------------------------------------------
+
+_TRAILING_PUNCT_RE = re.compile(r'[.,;:!?\)\]]+$')
+
+
+def _try_hyphen_join(
+    word_text: str,
+    next_word_text: str,
+    max_missing: int = 3,
+) -> Optional[Tuple[str, str, float]]:
+    """Try joining two fragments with 0..max_missing interpolated chars.
+
+    Strips trailing punctuation from the continuation word before testing
+    (e.g. "künden," → "künden") so dictionary lookup succeeds.
+
+    Returns (joined_word, missing_chars, confidence) or None.
+    """
+    base = word_text.rstrip("-").rstrip()
+    # Strip trailing punctuation from continuation (commas, periods, etc.)
+    raw_continuation = next_word_text.lstrip()
+    continuation = _TRAILING_PUNCT_RE.sub('', raw_continuation)
+
+    if not base or not continuation:
+        return None
+
+    # 1. Direct join (no missing chars)
+    direct = base + continuation
+    if _is_known(direct):
+        return (direct, "", 0.95)
+
+    # 2. Try with 1..max_missing missing characters
+    # Use common letters, weighted by frequency in German/English
+    _COMMON_CHARS = "enristaldhgcmobwfkzpvjyxqu"
+
+    for n_missing in range(1, max_missing + 1):
+        for chars in itertools.product(_COMMON_CHARS[:15], repeat=n_missing):
+            candidate = base + "".join(chars) + continuation
+            if _is_known(candidate):
+                missing = "".join(chars)
+                # Confidence decreases with more missing chars
+                conf = 0.90 - (n_missing - 1) * 0.10
+                return (candidate, missing, conf)
+
+    return None
+
+
+def _try_spell_fix(
+    word_text: str, col_type: str = "",
+) -> Optional[Tuple[str, float, List[str]]]:
+    """Try to fix a single garbled gutter word via spellchecker.
+
+    Returns (best_correction, confidence, alternatives_list) or None.
+    The alternatives list contains other plausible corrections the user
+    can choose from (e.g. "stammelt" vs "stammeln").
+    """
+    if len(word_text) < _MIN_WORD_LEN_SPELL:
+        return None
+
+    # Strip trailing/leading parentheses and check if the bare word is valid.
+    # Words like "probieren)" or "(Englisch" are valid words with punctuation,
+    # not OCR errors. Don't suggest corrections for them.
+    stripped = word_text.strip("()")
+    if stripped and _is_known(stripped):
+        return None
+
+    # Determine language priority from column type
+    if "en" in col_type:
+        lang = "en"
+    elif "de" in col_type:
+        lang = "de"
+    else:
+        lang = "both"
+
+    candidates = _spell_candidates(word_text, lang=lang)
+    if not candidates and lang != "both":
+        candidates = _spell_candidates(word_text, lang="both")
+
+    if not candidates:
+        return None
+
+    # Preserve original casing
+    is_upper = word_text[0].isupper()
+
+    def _preserve_case(w: str) -> str:
+        if is_upper and w:
+            return w[0].upper() + w[1:]
+        return w
+
+    # Sort candidates by edit distance (closest first)
+    scored = []
+    for c in candidates:
+        dist = _edit_distance(word_text.lower(), c.lower())
+        scored.append((dist, c))
+    scored.sort(key=lambda x: x[0])
+
+    best_dist, best = scored[0]
+    best = _preserve_case(best)
+    conf = max(0.5, 1.0 - best_dist * 0.15)
+
+    # Build alternatives (all other candidates, also case-preserved)
+    alts = [_preserve_case(c) for _, c in scored[1:] if c.lower() != best.lower()]
+    # Limit to top 5 alternatives
+    alts = alts[:5]
+
+    return (best, conf, alts)
+
+
+def _edit_distance(a: str, b: str) -> int:
+    """Simple Levenshtein distance."""
+    if len(a) < len(b):
+        return _edit_distance(b, a)
+    if len(b) == 0:
+        return len(a)
+    prev = list(range(len(b) + 1))
+    for i, ca in enumerate(a):
+        curr = [i + 1]
+        for j, cb in enumerate(b):
+            cost = 0 if ca == cb else 1
+            curr.append(min(curr[j] + 1, prev[j + 1] + 1, prev[j] + cost))
+        prev = curr
+    return prev[len(b)]