ms-file-toolkit 0.4.0__py3-none-any.whl

ms_file_toolkit-0.4.0.dist-info/METADATA

@@ -0,0 +1,156 @@
+Metadata-Version: 2.4
+Name: ms-file-toolkit
+Version: 0.4.0
+Summary: Microsoft fayllarni (DOCX/XLSX/PPTX) o'qish va yozish uchun AI function-calling Python toolkit
+Author: muslihiddinlive
+License: MIT
+Project-URL: Homepage, https://github.com/muslihiddinlive/ms-file-toolkit
+Project-URL: Repository, https://github.com/muslihiddinlive/ms-file-toolkit
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Requires-Dist: python-docx>=1.1.0
+Requires-Dist: openpyxl>=3.1.0
+Requires-Dist: python-pptx>=0.6.23
+Requires-Dist: Pillow>=10.0.0
+Requires-Dist: pypdf>=4.0.0
+Requires-Dist: pdfplumber>=0.11.0
+Requires-Dist: reportlab>=4.0.0
+Provides-Extra: ai
+Requires-Dist: anthropic>=0.40.0; extra == "ai"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0.0; extra == "dev"
+
+# ms-file-toolkit
+
+Microsoft fayllarni va PDF'larni **o'qish va yozish** uchun Python toolkit — **AI function calling** (Claude, GPT va h.k.) uchun tayyor tool schemalari, **xavfsizlik nazorati**, **avtomatik format aniqlash** va **CLI** bilan.
+
+## O'rnatish
+
+```bash
+pip install -r requirements.txt
+```
+
+Yoki paket sifatida (PyPI'ga chiqarishga tayyor, CLI bilan birga o'rnatiladi):
+
+```bash
+pip install -e ".[ai,dev]"
+```
+
+## Qo'llab-quvvatlanadigan formatlar
+
+| Format                        | O'qish                                        | Yozish                                                                             |
+| ------------------------------ | ------------------------------------------------ | --------------------------------------------------------------------------------------- |
+| `.docx`                         | matn, jadvallar, metama'lumot                     | yaratish, matn qo'shish/almashtirish, sarlavha, rasm, sahifa bo'linishi                |
+| `.xlsx`                         | varaq nomlari, ma'lumotlar, o'lcham xulosasi      | yaratish, varaq/qator qo'shish, formula, formatlash, panellarni muzlatish, **diagramma** |
+| `.pptx`                         | slayd matnlari, slaydlar soni, notes              | yaratish, slayd/rasm qo'shish, fon rangi, **diagramma**                                 |
+| `.pdf`                          | matn, jadvallar, metama'lumot                     | yaratish, birlashtirish (merge), bo'lish (split)                                        |
+| `.doc` / `.xls` / `.ppt` (eski) | `read_legacy_file` — LibreOffice orqali            | —                                                                                          |
+| **Har qanday (avtomatik)**       | `read_any_file`, `get_file_info`                   | —                                                                                          |
+
+> Eski formatlar uchun tizimda **LibreOffice** (`soffice`) kerak: `apt-get install libreoffice`
+
+## Xavfsizlik
+
+Fayl yo'llari AI tomonidan tanlanadi, shuning uchun **path traversal** himoyasi o'rnatilgan (`ms_toolkit/security.py`):
+
+```bash
+export MS_TOOLKIT_BASE_DIR=/home/bot/user_files   # faqat shu papka ichidagi fayllarga ruxsat
+```
+
+```python
+dispatch("read_docx_text", {"file_path": "../../etc/passwd"})
+# -> {"error": "Xavfsizlik xatosi: ..."}
+```
+
+## CLI (terminal orqali)
+
+```bash
+ms-toolkit list                                                    # barcha tool'lar ro'yxati
+ms-toolkit run create_docx '{"file_path": "a.docx", "title": "Salom", "overwrite": true}'
+ms-toolkit run read_any_file '{"file_path": "hujjat.xlsx"}'
+```
+
+## Tez boshlash (API kalitisiz)
+
+```bash
+pip install -e ".[dev]"
+pytest tests/ -v          # 23 ta test
+python test_toolkit.py    # tezkor smoke-test
+```
+
+## Function calling bilan (Claude API)
+
+```python
+from ms_toolkit import TOOLS, dispatch
+import anthropic
+
+client = anthropic.Anthropic()
+response = client.messages.create(
+    model="claude-sonnet-5",
+    max_tokens=1024,
+    tools=TOOLS,
+    messages=[{"role": "user", "content": "test.xlsx faylida nechta qator bor?"}],
+)
+
+for block in response.content:
+    if block.type == "tool_use":
+        print(dispatch(block.name, block.input))
+```
+
+To'liq agentic misol: [`example.py`](example.py).
+
+## Diagramma qo'shish misoli
+
+```python
+from ms_toolkit import dispatch
+
+dispatch("add_xlsx_chart", {
+    "file_path": "hisobot.xlsx", "chart_type": "bar",
+    "data_range": "B1:B5", "categories_range": "A2:A5", "title": "Oylik savdo",
+})
+
+dispatch("add_pptx_chart", {
+    "file_path": "taqdimot.pptx", "chart_type": "pie",
+    "categories": ["A", "B", "C"], "series": {"2026": [40, 35, 25]},
+})
+```
+
+## Barcha tool'lar ro'yxati (36 ta)
+
+**DOCX (9):** `read_docx_text`, `read_docx_tables`, `get_docx_metadata`, `create_docx`, `append_docx_text`, `replace_docx_text`, `add_docx_heading`, `add_docx_image`, `add_docx_page_break`
+**XLSX (10):** `get_xlsx_sheet_names`, `read_xlsx_data`, `get_xlsx_summary`, `create_xlsx`, `add_xlsx_sheet`, `append_xlsx_rows`, `set_xlsx_formula`, `format_xlsx_cells`, `freeze_xlsx_panes`, `add_xlsx_chart`
+**PPTX (8):** `read_pptx_text`, `get_pptx_slide_count`, `extract_pptx_notes`, `create_pptx`, `add_pptx_slide`, `add_pptx_image`, `set_pptx_background_color`, `add_pptx_chart`
+**PDF (6):** `read_pdf_text`, `read_pdf_tables`, `get_pdf_metadata`, `create_pdf`, `merge_pdfs`, `split_pdf`
+**Eski formatlar (1):** `read_legacy_file`
+**Auto-detect (2):** `read_any_file`, `get_file_info`
+
+## Struktura
+
+```
+ms_toolkit/
+  __init__.py       # TOOLS, dispatch export qiladi
+  docx_tool.py / docx_writer.py     # Word
+  xlsx_tool.py / xlsx_writer.py     # Excel (+ chart)
+  pptx_tool.py / pptx_writer.py     # PowerPoint (+ chart)
+  pdf_tool.py / pdf_writer.py        # PDF
+  legacy_tool.py                       # Eski formatlar
+  auto_tool.py                          # Avtomatik format aniqlash
+  security.py                            # Path-traversal himoyasi
+  cli.py                                   # Terminal interfeysi (ms-toolkit)
+  schemas.py                                # AI uchun tool schemalari
+  registry.py                                 # tool_name -> funksiya dispatcher
+example.py, test_toolkit.py, tests/            # Misollar va testlar
+pyproject.toml                                    # pip/PyPI paketlash + CLI entry point
+```
+
+## PyPI'ga chiqarish
+
+```bash
+pip install build twine
+python -m build
+twine upload dist/*
+```
+
+## Litsenziya
+
+MIT

ms_file_toolkit-0.4.0.dist-info/RECORD

@@ -0,0 +1,20 @@
+ms_toolkit/__init__.py,sha256=Z1W5C3-JR1AOKaG7CjW5d7UhRjALO3GdQG1GD5fh9eY,135
+ms_toolkit/auto_tool.py,sha256=RPVPiRLxpJ9dhAETGQ-XdZPetSNmauyk3WOIevVFUIA,1898
+ms_toolkit/cli.py,sha256=t9oacvxJNHdj2gyDP4md7g4IcpNrqcNzfZ8qPL1MoA8,1919
+ms_toolkit/docx_tool.py,sha256=HlI_HHan6Yij2rc61vMuuMVq-HLor_Q5wHYDv1VsiHU,1370
+ms_toolkit/docx_writer.py,sha256=qiCxW9Y-sIoBaIVx9TKPILCY9KceD_GMeEqLy34nlhQ,4786
+ms_toolkit/legacy_tool.py,sha256=20Lg_Zi203KqqaGzLV7DO5qAzZk5IqlVPtll3IKnwzw,3703
+ms_toolkit/pdf_tool.py,sha256=3eTVF-NkwnEMwqKw1t5_v9-0jtqWbhDNzXHJvuHz82Q,1892
+ms_toolkit/pdf_writer.py,sha256=9obBykLonfvAUM7HikKeCuGxsuawCKSjJU9-QLrHpWo,2742
+ms_toolkit/pptx_tool.py,sha256=5ylNTcJO0xuuwTuMidvqw3hIuidBY_6iCQh5DmZHDqw,1450
+ms_toolkit/pptx_writer.py,sha256=8nsC2f-SorRadnc_gDv24vVXDXzSUv8dNVsvYAUxxrs,5903
+ms_toolkit/registry.py,sha256=aERykycNpWDMRbY67ZxlmNgn0g0I3njfpJ3h_Y5VkhI,4775
+ms_toolkit/schemas.py,sha256=fcSXwmh2uJJrCpTY3_CEtBB9ursF_-C0WAIAIxTjznM,22530
+ms_toolkit/security.py,sha256=kFeM28aSZvDd_lWH-XHG6yInueAOzN_5xvcw0cbOPTU,2158
+ms_toolkit/xlsx_tool.py,sha256=olL3fRFMVene9K3eTsc4rsyFVG_uo5zEYGnqg6c48Ko,1604
+ms_toolkit/xlsx_writer.py,sha256=XgeOrzaOxnmGtueNn3qgNLGOXgS9gK81Z--Q_WwW76c,6190
+ms_file_toolkit-0.4.0.dist-info/METADATA,sha256=oKUusuS9JM1Axbur1EGKIDFh2sD4QQLC_FJPKqfTYxs,6250
+ms_file_toolkit-0.4.0.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
+ms_file_toolkit-0.4.0.dist-info/entry_points.txt,sha256=CwTAHXr0k41Nw92z9BierGPbxik9JX1vtqji0n8HfqM,51
+ms_file_toolkit-0.4.0.dist-info/top_level.txt,sha256=BMiFZC5zXYxp0YXqWU8kY2x2mQvEWbGe5Av_ShLEA40,11
+ms_file_toolkit-0.4.0.dist-info/RECORD,,

ms_file_toolkit-0.4.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.0.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

ms_file_toolkit-0.4.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+ms-toolkit = ms_toolkit.cli:main

ms_file_toolkit-0.4.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+ms_toolkit

ms_toolkit/__init__.py

@@ -0,0 +1,5 @@
+from .schemas import TOOLS
+from .registry import dispatch, REGISTRY
+
+__all__ = ["TOOLS", "dispatch", "REGISTRY"]
+__version__ = "0.4.0"

ms_toolkit/auto_tool.py

@@ -0,0 +1,61 @@
+"""Fayl turini avtomatik aniqlab, mos reader'ni chaqiradigan yordamchi modul."""
+
+import os
+
+_EXT_MAP = {
+    ".docx": "docx",
+    ".xlsx": "xlsx",
+    ".pptx": "pptx",
+    ".pdf": "pdf",
+    ".doc": "legacy",
+    ".xls": "legacy",
+    ".ppt": "legacy",
+}
+
+
+def get_file_info(file_path: str) -> dict:
+    """Fayl haqida asosiy ma'lumot: mavjudmi, kengaytmasi, hajmi, aniqlangan turi."""
+    ext = os.path.splitext(file_path)[1].lower()
+    exists = os.path.exists(file_path)
+    return {
+        "file_path": file_path,
+        "exists": exists,
+        "extension": ext,
+        "detected_type": _EXT_MAP.get(ext, "unknown"),
+        "size_bytes": os.path.getsize(file_path) if exists else None,
+    }
+
+
+def read_any_file(file_path: str) -> dict:
+    """Fayl kengaytmasiga qarab mos o'qish funksiyasini avtomatik tanlab chaqiradi.
+
+    Foydalanuvchi/AI fayl turini oldindan bilmasa yoki noaniq bo'lsa foydali —
+    .docx/.xlsx/.pptx va eski .doc/.xls/.ppt formatlarni avtomatik aniqlaydi.
+    """
+    from .docx_tool import read_docx_text
+    from .xlsx_tool import read_xlsx_data
+    from .pptx_tool import read_pptx_text
+    from .pdf_tool import read_pdf_text
+    from .legacy_tool import read_legacy_file
+
+    if not os.path.exists(file_path):
+        return {"error": f"Fayl topilmadi: {file_path}"}
+
+    ext = os.path.splitext(file_path)[1].lower()
+    kind = _EXT_MAP.get(ext)
+
+    if kind == "docx":
+        result = read_docx_text(file_path)
+    elif kind == "xlsx":
+        result = read_xlsx_data(file_path)
+    elif kind == "pptx":
+        result = read_pptx_text(file_path)
+    elif kind == "pdf":
+        result = read_pdf_text(file_path)
+    elif kind == "legacy":
+        result = read_legacy_file(file_path)
+    else:
+        return {"error": f"Qo'llab-quvvatlanmaydigan yoki noma'lum fayl turi: {ext or '(kengaytmasiz)'}"}
+
+    result["detected_type"] = kind
+    return result

ms_toolkit/cli.py

@@ -0,0 +1,61 @@
+"""
+ms_toolkit uchun komandalar qatori (CLI) interfeysi.
+
+Ishlatish:
+    ms-toolkit list
+    ms-toolkit run create_docx '{"file_path": "test.docx", "title": "Salom"}'
+    ms-toolkit run read_docx_text '{"file_path": "test.docx"}'
+    ms-toolkit run read_any_file '{"file_path": "hujjat.xlsx"}'
+
+MS_TOOLKIT_BASE_DIR muhit o'zgaruvchisi bilan fayl amallarini bitta papkaga
+cheklash mumkin (xavfsizlik uchun tavsiya etiladi).
+"""
+
+import sys
+import json
+import argparse
+
+from .registry import REGISTRY, dispatch
+from .schemas import TOOLS
+
+
+def cmd_list(args):
+    for t in TOOLS:
+        print(f"{t['name']:<28} {t['description'][:80]}")
+
+
+def cmd_run(args):
+    if args.tool_name not in REGISTRY:
+        print(f"Xato: noma'lum tool '{args.tool_name}'. Ro'yxat uchun: ms-toolkit list", file=sys.stderr)
+        sys.exit(1)
+
+    try:
+        tool_input = json.loads(args.json_input)
+    except json.JSONDecodeError as e:
+        print(f"Xato: JSON noto'g'ri formatda: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    result = dispatch(args.tool_name, tool_input)
+    print(json.dumps(result, ensure_ascii=False, indent=2, default=str))
+
+    if "error" in result:
+        sys.exit(1)
+
+
+def main():
+    parser = argparse.ArgumentParser(prog="ms-toolkit", description="MS fayllar (DOCX/XLSX/PPTX/PDF) uchun CLI")
+    sub = parser.add_subparsers(dest="command", required=True)
+
+    sub.add_parser("list", help="Barcha mavjud tool'larni ro'yxatini chiqaradi").set_defaults(func=cmd_list)
+
+    run_parser = sub.add_parser("run", help="Bitta tool'ni ishga tushiradi")
+    run_parser.add_argument("tool_name", help="Ishga tushiriladigan tool nomi (masalan: create_docx)")
+    run_parser.add_argument("json_input", help="Tool uchun JSON formatidagi kirish, masalan '{\"file_path\": \"a.docx\"}'")
+    run_parser.set_defaults(func=cmd_run)
+
+    args = parser.parse_args()
+    args.func(args)
+
+
+if __name__ == "__main__":
+    main()

ms_toolkit/docx_tool.py

@@ -0,0 +1,41 @@
+"""DOCX (Word) fayllarni o'qish va tahlil qilish funksiyalari."""
+
+from docx import Document
+
+
+def read_docx_text(file_path: str) -> dict:
+    """Word hujjatidagi barcha matnni paragraflar bo'yicha o'qiydi."""
+    doc = Document(file_path)
+    paragraphs = [p.text for p in doc.paragraphs if p.text.strip()]
+    return {
+        "file_path": file_path,
+        "paragraph_count": len(paragraphs),
+        "text": "\n".join(paragraphs),
+    }
+
+
+def read_docx_tables(file_path: str) -> dict:
+    """Word hujjatidagi barcha jadvallarni o'qiydi."""
+    doc = Document(file_path)
+    tables = []
+    for table in doc.tables:
+        rows = []
+        for row in table.rows:
+            rows.append([cell.text for cell in row.cells])
+        tables.append(rows)
+    return {"file_path": file_path, "table_count": len(tables), "tables": tables}
+
+
+def get_docx_metadata(file_path: str) -> dict:
+    """Word hujjatining metama'lumotlarini (muallif, sarlavha va h.k.) qaytaradi."""
+    doc = Document(file_path)
+    props = doc.core_properties
+    return {
+        "file_path": file_path,
+        "title": props.title,
+        "author": props.author,
+        "created": str(props.created) if props.created else None,
+        "modified": str(props.modified) if props.modified else None,
+        "paragraph_count": len(doc.paragraphs),
+        "table_count": len(doc.tables),
+    }

ms_toolkit/docx_writer.py

@@ -0,0 +1,141 @@
+"""DOCX (Word) fayllarni yaratish va tahrirlash (yozish) funksiyalari."""
+
+import os
+from docx import Document
+from docx.shared import Pt, Inches
+from docx.enum.text import WD_BREAK
+
+
+def create_docx(
+    file_path: str,
+    title: str = None,
+    paragraphs: list = None,
+    table_data: list = None,
+    overwrite: bool = False,
+) -> dict:
+    """Yangi Word (.docx) hujjat yaratadi.
+
+    paragraphs: matn qatorlari ro'yxati (har biri alohida paragraf bo'ladi).
+    table_data: jadval uchun 2-o'lchamli ro'yxat, masalan
+        [["Ism", "Yosh"], ["Ali", "25"], ["Vali", "30"]] — birinchi qator sarlavha
+        sifatida qalin (bold) qilib chiqariladi.
+    """
+    if os.path.exists(file_path) and not overwrite:
+        return {"error": f"Fayl allaqachon mavjud: {file_path} (overwrite=True qiling)"}
+
+    doc = Document()
+
+    if title:
+        doc.add_heading(title, level=1)
+
+    for para in paragraphs or []:
+        doc.add_paragraph(para)
+
+    if table_data:
+        rows = len(table_data)
+        cols = len(table_data[0]) if rows else 0
+        if rows and cols:
+            table = doc.add_table(rows=rows, cols=cols)
+            table.style = "Light Grid Accent 1"
+            for r, row_data in enumerate(table_data):
+                for c, cell_value in enumerate(row_data):
+                    cell = table.cell(r, c)
+                    cell.text = str(cell_value)
+                    if r == 0:
+                        for p in cell.paragraphs:
+                            for run in p.runs:
+                                run.font.bold = True
+
+    os.makedirs(os.path.dirname(os.path.abspath(file_path)) or ".", exist_ok=True)
+    doc.save(file_path)
+
+    return {
+        "file_path": file_path,
+        "status": "created",
+        "paragraph_count": len(paragraphs or []),
+        "table_added": bool(table_data),
+    }
+
+
+def append_docx_text(file_path: str, text: str, bold: bool = False) -> dict:
+    """Mavjud Word hujjatining oxiriga yangi paragraf qo'shadi."""
+    if not os.path.exists(file_path):
+        return {"error": f"Fayl topilmadi: {file_path}"}
+
+    doc = Document(file_path)
+    p = doc.add_paragraph()
+    run = p.add_run(text)
+    run.bold = bold
+    doc.save(file_path)
+
+    return {"file_path": file_path, "status": "appended", "paragraph_count": len(doc.paragraphs)}
+
+
+def replace_docx_text(file_path: str, find: str, replace: str, save_as: str = None) -> dict:
+    """Hujjatdagi barcha 'find' matnini 'replace' bilan almashtiradi.
+
+    save_as berilmasa, asl faylning ustiga yoziladi.
+    """
+    if not os.path.exists(file_path):
+        return {"error": f"Fayl topilmadi: {file_path}"}
+
+    doc = Document(file_path)
+    replacements = 0
+
+    for p in doc.paragraphs:
+        if find in p.text:
+            for run in p.runs:
+                if find in run.text:
+                    run.text = run.text.replace(find, replace)
+                    replacements += 1
+
+    for table in doc.tables:
+        for row in table.rows:
+            for cell in row.cells:
+                if find in cell.text:
+                    cell.text = cell.text.replace(find, replace)
+                    replacements += 1
+
+    out_path = save_as or file_path
+    doc.save(out_path)
+
+    return {"file_path": out_path, "status": "replaced", "replacements": replacements}
+
+
+def add_docx_heading(file_path: str, text: str, level: int = 1) -> dict:
+    """Mavjud Word hujjatiga sarlavha (heading, 1-9 daraja) qo'shadi."""
+    if not os.path.exists(file_path):
+        return {"error": f"Fayl topilmadi: {file_path}"}
+    if not 0 <= level <= 9:
+        return {"error": "level 0 dan 9 gacha bo'lishi kerak"}
+
+    doc = Document(file_path)
+    doc.add_heading(text, level=level)
+    doc.save(file_path)
+    return {"file_path": file_path, "status": "heading_added", "level": level}
+
+
+def add_docx_image(file_path: str, image_path: str, width_inches: float = 6.0) -> dict:
+    """Mavjud Word hujjatining oxiriga rasm qo'shadi."""
+    if not os.path.exists(file_path):
+        return {"error": f"Hujjat topilmadi: {file_path}"}
+    if not os.path.exists(image_path):
+        return {"error": f"Rasm fayli topilmadi: {image_path}"}
+
+    doc = Document(file_path)
+    doc.add_picture(image_path, width=Inches(width_inches))
+    doc.save(file_path)
+    return {"file_path": file_path, "status": "image_added", "image_path": image_path}
+
+
+def add_docx_page_break(file_path: str) -> dict:
+    """Mavjud Word hujjatining oxiriga sahifa bo'linishi (page break) qo'shadi."""
+    if not os.path.exists(file_path):
+        return {"error": f"Fayl topilmadi: {file_path}"}
+
+    doc = Document(file_path)
+    p = doc.add_paragraph()
+    run = p.add_run()
+    run.add_break(WD_BREAK.PAGE)
+    doc.save(file_path)
+    return {"file_path": file_path, "status": "page_break_added"}

ms_toolkit/legacy_tool.py

@@ -0,0 +1,114 @@
+"""
+Eski Microsoft formatlarini (.doc, .xls, .ppt) LibreOffice (soffice) yordamida
+yangi formatga (.docx, .xlsx, .pptx) konvertatsiya qilib, keyin mavjud
+docx_tool / xlsx_tool / pptx_tool funksiyalari bilan o'qish uchun modul.
+
+Talab: tizimda `soffice` (LibreOffice) o'rnatilgan bo'lishi kerak.
+"""
+
+import os
+import subprocess
+import tempfile
+import uuid
+
+_LEGACY_MAP = {
+    ".doc": "docx",
+    ".xls": "xlsx",
+    ".ppt": "pptx",
+}
+
+
+def is_legacy_format(file_path: str) -> bool:
+    """Fayl eski (.doc/.xls/.ppt) formatdami — shuni tekshiradi."""
+    ext = os.path.splitext(file_path)[1].lower()
+    return ext in _LEGACY_MAP
+
+
+def convert_legacy_file(file_path: str, timeout: int = 60) -> str:
+    """Eski formatdagi faylni vaqtinchalik papkada yangi formatga o'giradi.
+
+    Qaytaradi: yangi (.docx/.xlsx/.pptx) faylning to'liq yo'li.
+    Chaqiruvchi tugagach vaqtinchalik faylni o'zi tozalashi kerak (yoki
+    read_legacy_file wrapper'idan foydalaning — u avtomatik tozalaydi).
+    """
+    ext = os.path.splitext(file_path)[1].lower()
+    if ext not in _LEGACY_MAP:
+        raise ValueError(f"Qo'llab-quvvatlanmaydigan eski format: {ext}")
+
+    target_format = _LEGACY_MAP[ext]
+    out_dir = os.path.join(tempfile.gettempdir(), f"ms_toolkit_legacy_{uuid.uuid4().hex}")
+    os.makedirs(out_dir, exist_ok=True)
+
+    result = subprocess.run(
+        [
+            "soffice",
+            "--headless",
+            "--convert-to",
+            target_format,
+            "--outdir",
+            out_dir,
+            file_path,
+        ],
+        capture_output=True,
+        text=True,
+        timeout=timeout,
+    )
+
+    if result.returncode != 0:
+        raise RuntimeError(f"LibreOffice konvertatsiya xatosi: {result.stderr or result.stdout}")
+
+    base_name = os.path.splitext(os.path.basename(file_path))[0]
+    converted_path = os.path.join(out_dir, f"{base_name}.{target_format}")
+
+    if not os.path.exists(converted_path):
+        raise RuntimeError(
+            f"Konvertatsiya qilingan fayl topilmadi: {converted_path} (chiqish: {result.stdout})"
+        )
+
+    return converted_path
+
+
+def read_legacy_file(file_path: str) -> dict:
+    """Eski (.doc/.xls/.ppt) faylni avtomatik aniqlab, mos reader bilan o'qiydi.
+
+    Ichki ravishda yangi formatga o'giradi, tegishli o'qish funksiyasini
+    chaqiradi va natijaga original fayl yo'li va formatni qo'shib qaytaradi.
+    """
+    from .docx_tool import read_docx_text
+    from .xlsx_tool import read_xlsx_data
+    from .pptx_tool import read_pptx_text
+
+    ext = os.path.splitext(file_path)[1].lower()
+    if ext not in _LEGACY_MAP:
+        return {"error": f"Qo'llab-quvvatlanmaydigan eski format: {ext}"}
+
+    if not os.path.exists(file_path):
+        return {"error": f"Fayl topilmadi: {file_path}"}
+
+    converted_path = None
+    try:
+        converted_path = convert_legacy_file(file_path)
+        target_format = _LEGACY_MAP[ext]
+
+        if target_format == "docx":
+            result = read_docx_text(converted_path)
+        elif target_format == "xlsx":
+            result = read_xlsx_data(converted_path)
+        else:
+            result = read_pptx_text(converted_path)
+
+        result["original_file"] = file_path
+        result["original_format"] = ext
+        return result
+    except subprocess.TimeoutExpired:
+        return {"error": "Konvertatsiya vaqti tugadi (timeout)"}
+    except Exception as e:
+        return {"error": f"{type(e).__name__}: {e}"}
+    finally:
+        if converted_path and os.path.exists(converted_path):
+            out_dir = os.path.dirname(converted_path)
+            try:
+                os.remove(converted_path)
+                os.rmdir(out_dir)
+            except OSError:
+                pass

ms_toolkit/pdf_tool.py

@@ -0,0 +1,56 @@
+"""PDF fayllarni o'qish funksiyalari (pdfplumber — matn/jadval, pypdf — metama'lumot)."""
+
+import os
+import pdfplumber
+from pypdf import PdfReader
+
+
+def read_pdf_text(file_path: str, max_pages: int = None) -> dict:
+    """PDF fayldan barcha (yoki birinchi max_pages ta) sahifa matnini o'qiydi."""
+    if not os.path.exists(file_path):
+        return {"error": f"Fayl topilmadi: {file_path}"}
+
+    pages_text = []
+    with pdfplumber.open(file_path) as pdf:
+        pages = pdf.pages[:max_pages] if max_pages else pdf.pages
+        for i, page in enumerate(pages):
+            pages_text.append(page.extract_text() or "")
+
+    return {
+        "file_path": file_path,
+        "page_count": len(pages_text),
+        "text": "\n\n".join(pages_text),
+    }
+
+
+def read_pdf_tables(file_path: str) -> dict:
+    """PDF fayldagi har bir sahifadan jadvallarni ajratib oladi."""
+    if not os.path.exists(file_path):
+        return {"error": f"Fayl topilmadi: {file_path}"}
+
+    all_tables = []
+    with pdfplumber.open(file_path) as pdf:
+        for page_num, page in enumerate(pdf.pages, start=1):
+            for table in page.extract_tables():
+                all_tables.append({"page": page_num, "table": table})
+
+    return {"file_path": file_path, "table_count": len(all_tables), "tables": all_tables}
+
+
+def get_pdf_metadata(file_path: str) -> dict:
+    """PDF faylning metama'lumotini (sarlavha, muallif, sahifalar soni) qaytaradi."""
+    if not os.path.exists(file_path):
+        return {"error": f"Fayl topilmadi: {file_path}"}
+
+    reader = PdfReader(file_path)
+    meta = reader.metadata or {}
+
+    return {
+        "file_path": file_path,
+        "page_count": len(reader.pages),
+        "title": meta.get("/Title"),
+        "author": meta.get("/Author"),
+        "subject": meta.get("/Subject"),
+        "creator": meta.get("/Creator"),
+        "encrypted": reader.is_encrypted,
+    }