v1.0

agent/input_parser.py

@@ -0,0 +1,330 @@
+# agent/input_parser.py
+import re
+import os
+from typing import List, Dict, Optional, Tuple
+
+from agent.models import (
+    FileInfo, KeyInfo, ModuleInfo, ProgramMeta, CopyField, TableColumn, TableInfo
+)
+from agent.markdown_utils import (
+    extract_section, parse_table_rows, parse_table_from_section, find_row_by_key
+)
+
+
+class InputParser:
+    """解析 COBOL 程序的详细设计书和相关文件。"""
+
+    def __init__(self, design_md_path: str, source_cbl_path: str,
+                 file_db_md_path: str, cpy_dir: str, db_md_path: str):
+        self.design_md_path = design_md_path
+        self.source_cbl_path = source_cbl_path
+        self.file_db_md_path = file_db_md_path
+        self.cpy_dir = cpy_dir
+        self.db_md_path = db_md_path
+        self._design_text = ''
+        self._source_text = ''
+
+    def run(self) -> ProgramMeta:
+        """执行完整解析，返回 ProgramMeta。"""
+        self._design_text = self._read_file(self.design_md_path)
+        self._source_text = self._read_file(self.source_cbl_path)
+
+        meta = ProgramMeta(
+            program_id='', program_name='', system_name='',
+            pgm_type='', pgm_pattern='',
+            summary_lines=[], prerequisites=[],
+            files=[], keys=[], modules=[],
+            process_detail='', output_records='',
+            input_type='file',
+            copy_fields={}, db_tables={}
+        )
+
+        self._parse_basic_info(meta)
+        self._parse_use_files(meta)
+        self._parse_keys(meta)
+        self._parse_modules(meta)
+        self._parse_process_detail(meta)
+        self._parse_output_records(meta)
+        self._determine_input_type(meta)
+        self._parse_copybooks(meta)
+        self._parse_db_definition(meta)
+
+        return meta
+
+    def _parse_copybooks(self, meta: ProgramMeta):
+        replacing_list = self._extract_copy_replacing()
+
+        for f in meta.files:
+            if not f.copy_group:
+                continue
+
+            copy_file = os.path.join(self.cpy_dir, f.copy_group + '.cpy')
+            if not os.path.exists(copy_file):
+                continue
+
+            prefix = f.identifier
+            for i, (cpy_name, rep_val) in enumerate(replacing_list):
+                if cpy_name == f.copy_group and rep_val == f.identifier:
+                    prefix = rep_val
+                    replacing_list.pop(i)
+                    break
+            else:
+                for i, (cpy_name, rep_val) in enumerate(replacing_list):
+                    if cpy_name == f.copy_group:
+                        prefix = rep_val
+                        replacing_list.pop(i)
+                        break
+
+            fields = self._parse_single_copybook(copy_file, prefix)
+            if f.identifier not in meta.copy_fields:
+                meta.copy_fields[f.identifier] = fields
+
+    def _parse_db_definition(self, meta: ProgramMeta):
+        """解析 DB 定义书 .md，提取表结构信息。
+        只在输入类型涉及 DB 时调用。
+        """
+        if meta.input_type not in ('db', 'mixed'):
+            return
+
+        db_text = self._read_file(self.db_md_path)
+
+        sections = re.split(r'\n# ', db_text)
+
+        for section in sections:
+            table_match = re.match(r'^([\w\-]+)', section)
+            if not table_match:
+                continue
+            table_name = table_match.group(1)
+
+            section_with_header = '## ' + section
+
+            db_info_text = extract_section(section_with_header, 'DB基本情報')
+            db_info_rows = parse_table_rows(db_info_text)
+
+            db_id = ''
+            copy_id = ''
+            for row in db_info_rows:
+                db_id = row.get('DB ID', '') or db_id
+                copy_id = row.get('COPY ID', '') or copy_id
+
+            column_text = extract_section(section_with_header, 'カラム定義')
+            column_rows = parse_table_rows(column_text)
+
+            if not column_rows:
+                continue
+
+            columns = []
+            pk_columns = []
+            for row in column_rows:
+                try:
+                    no = int(row.get('No', '0'))
+                except ValueError:
+                    continue
+
+                is_pk = row.get('PK', '') == '✓'
+                nullable = row.get('NULL', 'NULL許可') == 'NULL許可'
+
+                col = TableColumn(
+                    no=no,
+                    name_jp=row.get('項目名', ''),
+                    name_en=row.get('項目名(英字名)', ''),
+                    type=row.get('TYPE', ''),
+                    max_len=row.get('最大長', ''),
+                    decimal_digits=row.get('小数桁', ''),
+                    byte_count=row.get('バイト数', ''),
+                    nullable=nullable,
+                    is_pk=is_pk
+                )
+                columns.append(col)
+                if is_pk:
+                    pk_columns.append(col.name_en)
+
+            table = TableInfo(
+                table_name=table_name,
+                db_id=db_id,
+                copy_id=copy_id,
+                columns=columns,
+                pk_columns=pk_columns
+            )
+            meta.db_tables[table_name] = table
+
+    def _extract_copy_replacing(self) -> List[Tuple[str, str]]:
+        """从 COBOL 源码提取 COPY ... REPLACING ... 映射。
+        Returns: [(copy_name, replacing_value), ...]  按出现顺序保存。
+        """
+        result = []
+        pattern = r'COPY\s+(\S+)\s+REPLACING\s+==\(A\)==\s+BY\s+==(\S+)=='
+        for match in re.finditer(pattern, self._source_text, re.IGNORECASE):
+            result.append((match.group(1), match.group(2)))
+        return result
+
+    def _parse_single_copybook(self, copy_path: str, prefix: str) -> List[CopyField]:
+        copy_text = self._read_file(copy_path)
+        fields = []
+
+        for line in copy_text.split('\n'):
+            line = line.strip()
+            if not line or line.startswith('*'):
+                continue
+
+            match = re.match(
+                r'(\d{2})\s+\(A\)(\S+)\s+PIC\s+(.+?)\.',
+                line, re.IGNORECASE
+            )
+            if not match:
+                continue
+
+            level = int(match.group(1))
+            raw_name = '(A)' + match.group(2)
+            pic_full = match.group(3).strip()
+            actual_name = prefix + '-' + match.group(2)
+            pic_bytes = self._calculate_pic_bytes(pic_full)
+
+            fields.append(CopyField(
+                level=level,
+                name=actual_name,
+                raw_name=raw_name,
+                pic_type=pic_full,
+                pic_bytes=pic_bytes
+            ))
+
+        return fields
+
+    @staticmethod
+    def _calculate_pic_bytes(pic: str) -> int:
+        pic_upper = pic.upper().strip()
+
+        if 'COMP-3' in pic_upper:
+            base = pic_upper.replace('COMP-3', '').strip()
+            total_digits = sum(int(num) for num in re.findall(r'9\((\d+)\)', base))
+            if base.startswith('S'):
+                return (total_digits + 2) // 2
+            else:
+                return (total_digits + 1) // 2
+
+        if 'COMP' in pic_upper or 'BINARY' in pic_upper:
+            base = re.sub(r'\s*(COMP|BINARY)\s*', '', pic_upper).strip()
+            total_digits = sum(int(num) for num in re.findall(r'9\((\d+)\)', base))
+            if total_digits <= 4:
+                return 2
+            elif total_digits <= 9:
+                return 4
+            else:
+                return 8
+
+        total = 0
+        for num in re.findall(r'X\((\d+)\)', pic_upper):
+            total += int(num)
+        for num in re.findall(r'G\((\d+)\)', pic_upper):
+            total += int(num) * 2
+        for num in re.findall(r'9\((\d+)\)', pic_upper):
+            total += int(num)
+        if total > 0:
+            return total
+
+        return 0
+
+    @staticmethod
+    def _read_file(path: str) -> str:
+        with open(path, 'r', encoding='utf-8') as f:
+            return f.read()
+
+    def _parse_basic_info(self, meta: ProgramMeta):
+        rows = parse_table_from_section(self._design_text, '基本情報')
+        for row in rows:
+            item = row.get('項目', '')
+            value = row.get('内容', '')
+            if item == 'システム名':
+                meta.system_name = value
+            elif item == 'プログラムID':
+                meta.program_id = value
+            elif item == 'プログラム名':
+                meta.program_name = value
+            elif item == 'PGMタイプ':
+                meta.pgm_type = value
+            elif item == 'PGMパターン':
+                meta.pgm_pattern = value
+            elif item == '機能概要':
+                meta.summary_lines.append(value)
+            elif item == '':
+                if value:
+                    meta.summary_lines.append(value)
+
+    def _parse_use_files(self, meta: ProgramMeta):
+        rows = parse_table_from_section(self._design_text, '使用ファイル一覧')
+        for row in rows:
+            try:
+                no_str = row.get('NO', '0')
+                try:
+                    no = int(no_str) if no_str and no_str.strip() not in ('', '—') else 0
+                except ValueError:
+                    no = 0
+                rec_len_str = row.get('レコード長', '0')
+                try:
+                    rec_len = int(rec_len_str) if rec_len_str and rec_len_str.strip() not in ('', '—') else 0
+                except ValueError:
+                    rec_len = 0
+                f = FileInfo(
+                    no=no,
+                    file_db_name=row.get('使用ファイル/DB名', ''),
+                    identifier=row.get('識別子', ''),
+                    dd_name=row.get('DD名', ''),
+                    io=row.get('I/O', ''),
+                    copy_group=row.get('COPY群', ''),
+                    format=row.get('形式', ''),
+                    record_len=rec_len,
+                    medium=row.get('媒体', ''),
+                    remarks=row.get('備考', '')
+                )
+                meta.files.append(f)
+            except (ValueError, KeyError):
+                continue
+
+    def _parse_keys(self, meta: ProgramMeta):
+        rows = parse_table_from_section(self._design_text, 'キー項目一覧')
+        for row in rows:
+            try:
+                k = KeyInfo(
+                    no=int(row.get('NO', '0')),
+                    file_name=row.get('ファイル名', ''),
+                    sort_condition=row.get('ソート条件(キー項目)', ''),
+                    key_condition=row.get('キー条件(マッチング/キーブレイク)', '')
+                )
+                meta.keys.append(k)
+            except (ValueError, KeyError):
+                continue
+
+    def _parse_modules(self, meta: ProgramMeta):
+        rows = parse_table_from_section(self._design_text, '使用モジュール一覧')
+        for row in rows:
+            try:
+                m = ModuleInfo(
+                    no=int(row.get('NO', '0')),
+                    function=row.get('機能', ''),
+                    program_id=row.get('プログラムID', ''),
+                    copy_name=row.get('使用COPY名', '')
+                )
+                meta.modules.append(m)
+            except (ValueError, KeyError):
+                continue
+
+    def _parse_process_detail(self, meta: ProgramMeta):
+        meta.process_detail = extract_section(self._design_text, '処理詳細')
+
+    def _parse_output_records(self, meta: ProgramMeta):
+        meta.output_records = extract_section(self._design_text, '出力レコード定義')
+
+    def _determine_input_type(self, meta: ProgramMeta):
+        input_mediums = set()
+        for f in meta.files:
+            if 'I' in f.io:
+                input_mediums.add(f.medium)
+
+        if not input_mediums:
+            meta.input_type = 'file'
+        elif input_mediums == {'PS'}:
+            meta.input_type = 'file'
+        elif input_mediums == {'DB'}:
+            meta.input_type = 'db'
+        else:
+            meta.input_type = 'mixed'