api/file_parser.py

"""
Multi-Detector File Parser for AES-Feedback.

Detects document structure using multiple strategies:
  - TableDetector: DOCX tables with Soal/Jawaban columns
  - SectionMarkerDetector: [URAIAN], [JAWABAN], SOAL:, JAWAB: markers
  - NumberedListDetector: numbered Soal-Jawaban pairs (1. 2. 3.)
  - KeywordDetector: heuristic keyword matching
  - SingleFallback: treat entire file as one essay

Each detector returns confidence (0.0-1.0) + extracted pairs.
Detector with highest confidence >= 0.7 determines multi-qa mode.
"""

import re
from typing import List, Optional, Tuple


class QAPair:
    """A single soal-jawaban pair."""
    def __init__(self, soal: str, jawaban: str):
        self.soal = soal.strip()
        self.jawaban = jawaban.strip()

    def __repr__(self):
        return f"QAPair(soal={self.soal[:40]}..., jawaban={self.jawaban[:40]}...)"


class DetectionResult:
    """Result from a single detector."""
    def __init__(self, strategy: str, confidence: float, pairs: List[QAPair]):
        self.strategy = strategy
        self.confidence = confidence
        self.pairs = pairs

    def __repr__(self):
        return f"DetectionResult(strategy={self.strategy}, confidence={self.confidence}, pairs={len(self.pairs)})"


class DocumentParser:
    """Extract text from .docx and .pdf files."""

    @staticmethod
    def extract_text_from_docx(path: str) -> Tuple[str, Optional[object]]:
        """Extract full text + doc object from .docx."""
        from docx import Document
        doc = Document(path)
        full_text = "\n".join(p.text for p in doc.paragraphs)
        return full_text, doc

    @staticmethod
    def extract_text_from_pdf(path: str) -> Tuple[str, None]:
        """Extract full text from .pdf."""
        import fitz
        doc = fitz.open(path)
        full_text = "\n".join(page.get_text() for page in doc)
        doc.close()
        return full_text, None

    @staticmethod
    def extract_text(path: str) -> Tuple[str, Optional[object]]:
        """Auto-detect file type and extract text."""
        if path.lower().endswith(".docx"):
            return DocumentParser.extract_text_from_docx(path)
        elif path.lower().endswith(".pdf"):
            return DocumentParser.extract_text_from_pdf(path)
        else:
            raise ValueError(f"Unsupported file format: {path}. Only .docx and .pdf are supported.")


class StructureDetector:
    """
    Run all detectors and select the best result.
    """

    def __init__(self, text: str, doc: Optional[object] = None):
        self.text = text
        self.doc = doc  # python-docx Document object (for table detection)

    def detect(self) -> DetectionResult:
        detectors = [
            ("table", self._detect_table),
            ("section_marker", self._detect_section_markers),
            ("numbered_list", self._detect_numbered_list),
            ("keyword", self._detect_keyword),
        ]

        best = DetectionResult("single", 0.0, self._single_fallback())

        for name, detector_fn in detectors:
            try:
                result = detector_fn()
                if result and result.confidence > best.confidence:
                    best = result
            except Exception:
                continue

        # If confidence >= 0.7, use multi-qa. Otherwise return single fallback.
        if best.confidence >= 0.7:
            return best
        return DetectionResult("single", 0.0, self._single_fallback())

    def _single_fallback(self) -> List[QAPair]:
        """Treat entire text as one essay."""
        return [QAPair("", self.text)]

    def _detect_table(self) -> Optional[DetectionResult]:
        """Detect Soal-Jawaban pairs from DOCX tables."""
        if self.doc is None:
            return None

        pairs = []
        for table in self.doc.tables:
            rows = table.rows
            if len(rows) < 2:
                continue

            headers = [cell.text.strip().lower() for cell in rows[0].cells]
            has_soal = any("soal" in h for h in headers)
            has_jawaban = any("jawaban" in h for h in headers)
            if not (has_soal and has_jawaban):
                continue

            # Find column indices
            soal_idx = next(i for i, h in enumerate(headers) if "soal" in h)
            jawaban_idx = next(i for i, h in enumerate(headers) if "jawaban" in h)

            for row in rows[1:]:
                cells = row.cells
                if soal_idx < len(cells) and jawaban_idx < len(cells):
                    soal = cells[soal_idx].text.strip()
                    jawaban = cells[jawaban_idx].text.strip()
                    if soal or jawaban:
                        pairs.append(QAPair(soal, jawaban))

        if pairs:
            confidence = min(1.0, 0.7 + 0.05 * len(pairs))
            return DetectionResult("table", confidence, pairs)
        return None

    def _detect_section_markers(self) -> Optional[DetectionResult]:
        """Detect pairs using section markers like [URAIAN], [JAWABAN], SOAL:, JAWAB:."""
        lines = self.text.strip().split("\n")
        sections = []
        current_section = None
        current_content = []

        section_patterns = [
            (r"\[URAIAN\]", "soal"),
            (r"\[JAWABAN\]", "jawaban"),
            (r"^SOAL\s*\d*\s*:", "soal"),
            (r"^JAWAB\s*\d*\s*:", "jawaban"),
            (r"^PERTANYAAN\s*\d*\s*:", "soal"),
            (r"^PERTANYAAN\s*\d*\s*\.", "soal"),
        ]

        for line in lines:
            matched = False
            for pattern, section_type in section_patterns:
                if re.search(pattern, line.strip(), re.IGNORECASE):
                    if current_section is not None:
                        sections.append((current_section, "\n".join(current_content).strip()))
                    current_section = section_type
                    # Remove the marker from content
                    cleaned = re.sub(pattern, "", line, flags=re.IGNORECASE).strip()
                    current_content = [cleaned] if cleaned else []
                    matched = True
                    break

            if not matched and current_section is not None:
                current_content.append(line)

        if current_section is not None:
            sections.append((current_section, "\n".join(current_content).strip()))

        if not sections:
            return None

        soals = [content for sec_type, content in sections if sec_type == "soal"]
        jawabans = [content for sec_type, content in sections if sec_type == "jawaban"]

        # If single combined section for each, try splitting by numbered items
        if len(soals) == 1 and len(jawabans) == 1:
            soal_items = self._split_numbered_items(soals[0])
            jawaban_items = self._split_numbered_items(jawabans[0])
            if len(soal_items) == len(jawaban_items) and len(soal_items) >= 2:
                pairs = [QAPair(soal_items[i], jawaban_items[i]) for i in range(len(soal_items))]
                confidence = 0.7 + 0.05 * min(len(pairs), 4)
                return DetectionResult("section_marker", min(confidence, 1.0), pairs)

        pairs = []
        for i, jawaban in enumerate(jawabans):
            soal = soals[i] if i < len(soals) else ""
            pairs.append(QAPair(soal, jawaban))

        if pairs:
            confidence = 0.7 + 0.05 * min(len(pairs), 4)
            return DetectionResult("section_marker", min(confidence, 1.0), pairs)
        return None

    def _split_numbered_items(self, text: str) -> List[str]:
        """Split text by numbered lines. Handles '1. text', '1) text', '1\\ntext'."""
        lines = text.strip().split("\n")
        items = []
        current = None
        started = False
        for line in lines:
            stripped = line.strip()
            if not stripped:
                continue
            if re.match(r"^(?:soal|jawaban|pertanyaan)s?\s*$", stripped, re.IGNORECASE):
                continue
            m = re.match(r"^(\d+)\s*$", stripped)
            if m:
                if current is not None:
                    items.append("\n".join(current).strip())
                current = []
                started = True
                continue
            m = re.match(r"^(\d+)\s*[\.\)]\s*(.+)", stripped)
            if m:
                if current is not None:
                    items.append("\n".join(current).strip())
                current = [m.group(2).strip()]
                started = True
                continue
            if started:
                if current is not None:
                    current.append(line)
        if current is not None:
            items.append("\n".join(current).strip())
        return items

    def _detect_numbered_list(self) -> Optional[DetectionResult]:
        """Detect numbered Soal-Jawaban pairs like 'Soal 1', 'Soal 2', etc."""
        lines = self.text.strip().split("\n")
        pairs = []

        # Try to detect alternating soals/jawabans
        soal_pattern = re.compile(r"^(?:Soal|Pertanyaan|SOAL|PERTANYAAN)\s*(\d+)\s*[\.:]?\s*(.*)", re.IGNORECASE)
        jawaban_pattern = re.compile(r"^(?:Jawaban|JAWABAN|JAWAB)\s*(\d+)\s*[\.:]?\s*(.*)", re.IGNORECASE)

        current_soal = {}
        current_jawaban = {}

        for line in lines:
            stripped = line.strip()
            if not stripped:
                continue

            m = soal_pattern.match(stripped)
            if m:
                idx = int(m.group(1))
                current_soal[idx] = m.group(2).strip()
                continue

            m = jawaban_pattern.match(stripped)
            if m:
                idx = int(m.group(1))
                current_jawaban[idx] = m.group(2).strip()
                continue

            # Check for simple numbered list: "1. text" or "1) text"
            m = re.match(r"^(\d+)\s*[\.\)]\s*(.+)", stripped)
            if m:
                idx = int(m.group(1))
                content = m.group(2).strip()
                # Try to classify as soal or jawaban by proximity or content
                if idx not in current_soal and idx not in current_jawaban:
                    # First pass: tentatively store both possibilities
                    current_soal[idx] = content

        # Try to match by index
        all_indices = sorted(set(list(current_soal.keys()) + list(current_jawaban.keys())))
        for idx in all_indices:
            soal = current_soal.get(idx, "")
            jawaban = current_jawaban.get(idx, "")
            if soal or jawaban:
                pairs.append(QAPair(soal, jawaban))

        if pairs and len(pairs) >= 2:
            confidence = 0.65 + 0.05 * min(len(pairs), 5)
            return DetectionResult("numbered_list", min(confidence, 1.0), pairs)
        return None

    def _detect_keyword(self) -> Optional[DetectionResult]:
        """Detect pairs using heuristic keyword matching."""
        text_lower = self.text.lower()
        lines = self.text.strip().split("\n")
        pairs = []

        # Find soal lines and jawaban lines by keyword density
        soal_keywords = {"soal", "pertanyaan", "uraian", "deskripsi", "soal:"}
        jawaban_keywords = {"jawaban", "jawab", "jawaban:", "jawab:"}

        current_soal = ""
        current_jawaban = ""
        mode = None

        for line in lines:
            stripped = line.strip()
            if not stripped:
                continue

            line_lower = stripped.lower()
            is_soal_line = any(kw in line_lower for kw in soal_keywords)
            is_jawaban_line = any(kw in line_lower for kw in jawaban_keywords)

            if is_soal_line and len(stripped) < 100:
                if current_jawaban and current_soal:
                    pairs.append(QAPair(current_soal, current_jawaban))
                current_soal = stripped
                current_jawaban = ""
                mode = "soal"
            elif is_jawaban_line and len(stripped) < 100:
                if current_soal and not current_jawaban:
                    current_jawaban = ""
                elif current_jawaban:
                    pairs.append(QAPair(current_soal, current_jawaban))
                    current_soal = ""
                    current_jawaban = ""
                mode = "jawaban"
            elif mode == "soal":
                current_soal += "\n" + stripped
            elif mode == "jawaban":
                current_jawaban += "\n" + stripped

        if current_soal or current_jawaban:
            pairs.append(QAPair(current_soal, current_jawaban))

        if pairs and len(pairs) >= 2:
            confidence = 0.6 + 0.05 * min(len(pairs), 4)
            return DetectionResult("keyword", min(confidence, 1.0), pairs)
        return None

    @staticmethod
    def parse(path: str) -> DetectionResult:
        """
        High-level API: parse a .docx or .pdf file and return detection result.

        Args:
            path: Path to .docx or .pdf file

        Returns:
            DetectionResult with strategy, confidence, and extracted QAPairs
        """
        text, doc = DocumentParser.extract_text(path)
        detector = StructureDetector(text, doc)
        return detector.detect()