ocr-postprocess 0.1.0__py3-none-any.whl

ocr_postprocess/transformer.py

@@ -0,0 +1,304 @@
+"""Transform pipeline: built-in ops and simpleeval compute."""
+
+from __future__ import annotations
+
+import datetime as _dt
+import logging
+import re
+from typing import Any, Callable
+
+from dateutil import parser as dateutil_parser
+from simpleeval import EvalWithCompoundTypes, InvalidExpression
+
+from ocr_postprocess.exceptions import CyclicComputeError, TransformError
+
+logger = logging.getLogger(__name__)
+
+_OPS: dict[str, Callable[..., Any]] = {}
+
+
+def transform_op(name: str):
+    """Decorator to register a transform op."""
+
+    def deco(fn: Callable) -> Callable:
+        _OPS[name] = fn
+        return fn
+
+    return deco
+
+
+# ---------------------------------------------------------------------------
+# Built-in ops
+# ---------------------------------------------------------------------------
+
+
+@transform_op("strip")
+def _strip(value: Any, **_: Any) -> Any:
+    return value.strip() if isinstance(value, str) else value
+
+
+@transform_op("upper")
+def _upper(value: Any, **_: Any) -> Any:
+    return value.upper() if isinstance(value, str) else value
+
+
+@transform_op("lower")
+def _lower(value: Any, **_: Any) -> Any:
+    return value.lower() if isinstance(value, str) else value
+
+
+@transform_op("replace")
+def _replace(value: Any, from_: str = "", to: str = "", **_: Any) -> Any:
+    if not isinstance(value, str):
+        return value
+    return value.replace(from_, to)
+
+
+@transform_op("regex_group")
+def _regex_group(value: Any, pattern: str = "", group: int = 1, **_: Any) -> Any:
+    if not isinstance(value, str):
+        return value
+    m = re.search(pattern, value)
+    if m:
+        try:
+            return m.group(group)
+        except IndexError:
+            return None
+    return None
+
+
+@transform_op("regex_sub")
+def _regex_sub(value: Any, pattern: str = "", repl: str = "", **_: Any) -> Any:
+    if not isinstance(value, str):
+        return value
+    return re.sub(pattern, repl, value)
+
+
+@transform_op("split_take")
+def _split_take(value: Any, sep: str = "/", index: int = 0, **_: Any) -> Any:
+    if not isinstance(value, str):
+        return value
+    parts = value.split(sep)
+    return parts[index].strip() if 0 <= index < len(parts) else None
+
+
+@transform_op("split_first")
+def _split_first(value: Any, sep: str = "/", **_: Any) -> Any:
+    return _split_take(value, sep=sep, index=0)
+
+
+@transform_op("strip_unit")
+def _strip_unit(value: Any, units: list[str] | None = None, **_: Any) -> Any:
+    if not isinstance(value, str):
+        return value
+    result = value.strip()
+    if units:
+        for unit in units:
+            escaped = re.escape(unit)
+            result = re.sub(rf"\s*{escaped}\s*$", "", result, flags=re.IGNORECASE).strip()
+    return result
+
+
+@transform_op("dedup_words")
+def _dedup_words(value: Any, **_: Any) -> Any:
+    if not isinstance(value, str):
+        return value
+    words = value.split()
+    deduped = []
+    for w in words:
+        if not deduped or w != deduped[-1]:
+            deduped.append(w)
+    return " ".join(deduped)
+
+
+@transform_op("to_int")
+def _to_int(value: Any, **_: Any) -> Any:
+    if isinstance(value, int):
+        return value
+    if isinstance(value, str):
+        cleaned = re.sub(r"[^\d\-]", "", value.replace(",", "").replace(".", ""))
+        try:
+            return int(cleaned)
+        except (ValueError, TypeError):
+            return None
+    return None
+
+
+@transform_op("to_float")
+def _to_float(value: Any, **_: Any) -> Any:
+    if isinstance(value, float):
+        return value
+    if isinstance(value, str):
+        cleaned = value.replace(",", ".").strip()
+        try:
+            return float(cleaned)
+        except (ValueError, TypeError):
+            return None
+    return None
+
+
+@transform_op("to_date")
+def _to_date(value: Any, format: str = "", output: str = "iso", **_: Any) -> Any:
+    if not isinstance(value, str):
+        return value
+    # Already ISO YYYY-MM-DD — return unchanged to avoid mis-parsing with dayfirst=True.
+    # Example: "2024-06-10" with dayfirst=True would become "2024-10-06" (wrong).
+    if re.fullmatch(r"\d{4}-\d{2}-\d{2}", value.strip()):
+        return value.strip()
+    try:
+        dt = dateutil_parser.parse(value, dayfirst=True)
+        if output == "iso":
+            return dt.date().isoformat()
+        return str(dt.date())
+    except (ValueError, TypeError):
+        return None
+
+
+@transform_op("pick")
+def _pick(value: Any, kind: str = "year", **_: Any) -> Any:
+    if not isinstance(value, str):
+        return value
+    if kind == "year":
+        m = re.search(r"\b(19|20)\d{2}\b", value)
+        return m.group(0) if m else None
+    return value
+
+
+@transform_op("enum_normalize")
+def _enum_normalize(value: Any, map: dict[str, str] | None = None, **_: Any) -> Any:
+    if not isinstance(value, str) or not map:
+        return value
+    return map.get(value, map.get(value.lower(), value))
+
+
+@transform_op("default_if_empty")
+def _default_if_empty(value: Any, default: Any = None, **_: Any) -> Any:
+    if value is None or value == "" or value == []:
+        return default
+    return value
+
+
+# ---------------------------------------------------------------------------
+# Apply pipeline
+# ---------------------------------------------------------------------------
+
+
+def _parse_op(op_ref: Any) -> tuple[str, dict[str, Any]]:
+    """Parse op reference from various YAML notations.
+
+    Supports:
+      "strip"                 -> ("strip", {})
+      {"op": "to_date", ...}  -> ("to_date", {...})
+      {"to_date": {...}}      -> ("to_date", {...})
+    """
+    if isinstance(op_ref, str):
+        return op_ref, {}
+    if isinstance(op_ref, dict):
+        if "op" in op_ref:
+            name = op_ref["op"]
+            args = {k: v for k, v in op_ref.items() if k != "op"}
+            return name, args
+        # single-key dict notation
+        if len(op_ref) == 1:
+            name = next(iter(op_ref))
+            args = op_ref[name] if isinstance(op_ref[name], dict) else {}
+            return name, args
+    raise TransformError(f"Cannot parse op reference: {op_ref!r}")
+
+
+def apply_transforms(value: Any, ops: list[Any]) -> Any:
+    """Apply a list of transform ops sequentially to value."""
+    for op_ref in ops:
+        name, args = _parse_op(op_ref)
+        if name not in _OPS:
+            raise TransformError(f"Unknown transform op: '{name}'")
+        try:
+            value = _OPS[name](value, **args)
+        except TransformError:
+            raise
+        except Exception as exc:
+            raise TransformError(f"Op '{name}' failed: {exc}") from exc
+        if value is None:
+            break
+    return value
+
+
+# ---------------------------------------------------------------------------
+# Compute (simpleeval)
+# ---------------------------------------------------------------------------
+
+_SAFE_FUNCTIONS = {
+    "min": min,
+    "max": max,
+    "abs": abs,
+    "round": round,
+    "len": len,
+    "str": str,
+    "int": int,
+    "float": float,
+    # Date helpers for compute expressions (e.g. year_now() - year(ngay_sinh))
+    "year_now": lambda: _dt.date.today().year,
+    "year": lambda s: _dt.date.fromisoformat(str(s)).year if s else None,
+    "month": lambda s: _dt.date.fromisoformat(str(s)).month if s else None,
+    "day": lambda s: _dt.date.fromisoformat(str(s)).day if s else None,
+}
+
+
+def compute_field(expr: str, deps: dict[str, Any]) -> Any:
+    """Evaluate a simpleeval expression with dep values as names.
+
+    Raises TransformError on eval failure.
+    """
+    evaluator = EvalWithCompoundTypes(names=deps, functions=_SAFE_FUNCTIONS)
+    try:
+        return evaluator.eval(expr)
+    except InvalidExpression as exc:
+        raise TransformError(f"compute expression failed: {exc!r}") from exc
+    except Exception as exc:
+        raise TransformError(f"compute expression error: {exc}") from exc
+
+
+# ---------------------------------------------------------------------------
+# Topological sort for compute fields
+# ---------------------------------------------------------------------------
+
+
+def topo_sort_compute(fields: list[dict[str, Any]]) -> list[str]:
+    """Return field keys in topological order based on compute deps.
+
+    Raises CyclicComputeError if cycle detected.
+    Only includes fields that have a 'compute' key.
+    """
+    compute_fields = {f["key"]: f for f in fields if f.get("compute")}
+
+    # Build adjacency: dep → [fields that depend on dep]
+    graph: dict[str, list[str]] = {k: [] for k in compute_fields}
+    in_degree: dict[str, int] = {k: 0 for k in compute_fields}
+
+    for key, field in compute_fields.items():
+        for dep in field.get("deps", []):
+            if dep in compute_fields:
+                graph[dep].append(key)
+                in_degree[key] += 1
+
+    # Kahn's algorithm
+    queue = [k for k, deg in in_degree.items() if deg == 0]
+    order: list[str] = []
+    while queue:
+        node = queue.pop(0)
+        order.append(node)
+        for dependent in graph.get(node, []):
+            in_degree[dependent] -= 1
+            if in_degree[dependent] == 0:
+                queue.append(dependent)
+
+    if len(order) != len(compute_fields):
+        cycle_keys = set(compute_fields) - set(order)
+        raise CyclicComputeError(f"Cyclic compute dependency detected: {cycle_keys}")
+
+    return order
+
+
+def all_op_names() -> list[str]:
+    """Return all registered op names."""
+    return list(_OPS.keys())

ocr_postprocess-0.1.0.dist-info/METADATA

@@ -0,0 +1,189 @@
+Metadata-Version: 2.4
+Name: ocr-postprocess
+Version: 0.1.0
+Summary: Biến raw OCR text thành structured document — trích xuất trường dữ liệu, xử lý nhiễu, cross-check, render JSON/Markdown.
+Home-page: https://github.com/ohmygodvt95/ocr-postprocess
+Author: ohmygodvt95
+License: MIT
+Keywords: ocr post-processing nlp document extraction vietnamese
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Text Processing
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: pydantic>=2.5
+Requires-Dist: PyYAML>=6.0
+Requires-Dist: rapidfuzz>=3.5
+Requires-Dist: regex>=2024.1.24
+Requires-Dist: typer>=0.12
+Requires-Dist: python-dateutil>=2.9
+Requires-Dist: simpleeval>=0.9.13
+Dynamic: author
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# ocr-postprocess
+
+Biến raw OCR text thành structured document — trích xuất trường dữ liệu, xử lý nhiễu, cross-check, và render ra JSON/Markdown.
+
+## Installation
+
+```bash
+pip install ocr-postprocess
+```
+
+Hoặc cài từ source:
+
+```bash
+git clone https://github.com/your-org/ocr-postprocess
+cd ocr-postprocess
+pip install -e .
+```
+
+## Library usage
+
+```python
+from ocr_postprocess import Pipeline, ProcessedDocument, OcrPostprocessError
+
+# Sử dụng profiles bundled sẵn (no extra files needed)
+pipeline = Pipeline.from_default()
+
+raw_text = open("scan.txt").read()
+
+try:
+    doc: ProcessedDocument = pipeline.process(raw_text)
+except OcrPostprocessError as exc:
+    print(f"Pipeline error: {exc}")
+    raise
+
+# Lấy một trường
+name_candidate = doc.get("ho_va_ten")
+if name_candidate:
+    print(name_candidate.value)       # "NGUYỄN VĂN A"
+    print(name_candidate.confidence)  # 0.91
+
+# Toàn bộ trường đã trích
+fields = {c.key: c.value for c in doc.candidates}
+
+# Export JSON
+import json
+print(json.dumps(doc.to_json(), ensure_ascii=False, indent=2))
+
+# Export Markdown
+print(doc.markdown)
+```
+
+### Custom profiles directory
+
+```python
+# Dùng thư mục profiles riêng
+pipeline = Pipeline.from_default(profiles_dir="my_profiles/")
+```
+
+### Classify only
+
+```python
+profile_id, score = pipeline.classify(raw_text)
+# "cccd_2024", 0.97
+```
+
+### ProcessedDocument fields
+
+| Field | Type | Mô tả |
+|---|---|---|
+| `profile_id` | `str` | Profile được match |
+| `profile_score` | `float` | Điểm classify (0–1) |
+| `candidates` | `list[Candidate]` | Tất cả trường đã trích |
+| `overall_confidence` | `float` | Điểm tin cậy tổng hợp |
+| `warnings` | `list[str]` | Cảnh báo từ pipeline |
+| `markdown` | `str` | Kết quả render Markdown |
+| `cross_checks` | `list[CrossCheck]` | Kết quả cross-check |
+
+## CLI
+
+```bash
+# Process a document
+ocrpp process scan.txt
+
+# Markdown output
+ocrpp process scan.txt --format markdown
+
+# Classify only
+ocrpp classify scan.txt
+
+# Validate a profile
+ocrpp validate-profile profiles/my_profile.yml
+
+# Custom profiles directory
+ocrpp process scan.txt --profiles ./my_profiles/
+```
+
+## Adding a custom profile
+
+Tạo file YAML trong thư mục profiles của bạn:
+
+```yaml
+id: my_doc
+version: 1
+display_name: "My document type"
+
+classify:
+  any_of:
+    - contains_any: ["MY DOCUMENT HEADER"]
+
+extract:
+  - name: document_number
+    aliases: ["Document No", "Số chứng từ"]
+    extractor: value_in_same_line
+    required: true
+```
+
+Sau đó:
+
+```python
+pipeline = Pipeline.from_default(profiles_dir="my_profiles/")
+```
+
+## Exceptions
+
+```python
+from ocr_postprocess import (
+    OcrPostprocessError,      # base
+    ProfileNotFoundError,
+    ProfileValidationError,
+    ExtractorNotFoundError,
+    TransformError,
+)
+```
+
+## Development
+
+```bash
+python -m venv .venv && source .venv/bin/activate
+pip install -r requirements-dev.txt
+pip install -e .
+
+pytest                    # all tests
+pytest tests/unit         # unit only
+pytest -m golden          # golden/regression
+pytest -n auto --cov      # parallel + coverage
+ruff check . && black --check .
+```
+
+## Docs
+
+Xem [docs/README.md](docs/README.md) để biết chi tiết về pipeline stages và profile schema.
+

ocr_postprocess-0.1.0.dist-info/RECORD

@@ -0,0 +1,55 @@
+ocr_postprocess/__init__.py,sha256=f5tskc50hqq_cbaWIRgrs6dw2_-2UKFk3c_hxG_bAiY,861
+ocr_postprocess/classifier.py,sha256=PENB6t0SWRzMxc9UGDj9nP4AFqWJHFYua3u0JXqWmFU,1986
+ocr_postprocess/cli.py,sha256=pSdg9nhpue8Ql-vf0O6SGk5gwctjipG_OAIidsxHB0w,4259
+ocr_postprocess/exceptions.py,sha256=lHa1r4B1b1TOPdElV3da-mYws-Uu7IQNBgCGCN-taFQ,856
+ocr_postprocess/models.py,sha256=9Fb7t5DT7CrcnKd2Vnmn1OSzHYFkxqCLkVSnXQMYCcA,4510
+ocr_postprocess/pipeline.py,sha256=QLEaU5Fjg0lj1LQvM573ZGM8Zz4o_41BOrTXq1h2W18,6637
+ocr_postprocess/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ocr_postprocess/scorer.py,sha256=i1bPKkWdBxJUq4GVVPxE7GSSkLhs0YgYKERZav3f9tk,2738
+ocr_postprocess/transformer.py,sha256=ouN5sZZAnQmB22AJr0oG5XmmxrzUiD0xrn1GTRLCNJ4,9349
+ocr_postprocess/engine/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ocr_postprocess/engine/denoiser.py,sha256=77UNAv75TlV4sVrLT5LHXLUnOdVQBn4UbJtDU0Pq6iQ,4345
+ocr_postprocess/engine/extractor_stage.py,sha256=ArpK-V0oVEkP2yKl_D2x68blCeeYSc4CORZc1TJ_y0Q,3423
+ocr_postprocess/engine/normalizer.py,sha256=BBqAzeyNV2wv-5ewu5SJMte-kjgo9jgVekimh7maQys,3878
+ocr_postprocess/engine/reconciler.py,sha256=ohxErHyn0PavcgUldnhfv442-HvEdtk6PlLyubooP8s,6156
+ocr_postprocess/engine/reconstructor.py,sha256=sVmn-8nygFTlT31aWe-uxbfGDdgEr1bwW-78fIfjuMo,16645
+ocr_postprocess/engine/transform_stage.py,sha256=DIz44lOUDQodS1hUmEtRGw2mF_dxfyPp1LTlzxt-xz4,3330
+ocr_postprocess/extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ocr_postprocess/extractors/base.py,sha256=u8bzVK0wxv3X-J_lfICEHwG-L__89j5w_XbDHErfChY,2857
+ocr_postprocess/extractors/helpers.py,sha256=kzY-g7KfGI1iySIN0oDzDqtLOE9fIMIVP551OqrSrs0,2141
+ocr_postprocess/extractors/registry.py,sha256=ULh_BoyUbC17VMdnXv1ffzFokZizJXfsxx53ziLbs3U,1092
+ocr_postprocess/extractors/universal.py,sha256=98IP5HfIneLeLHJsvXu1Spxado0XNAsbL_M-x-hEMM0,991
+ocr_postprocess/extractors/label_anchor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ocr_postprocess/extractors/label_anchor/line_after_label.py,sha256=gKFzsveaAerUxox-i3BvFSZWIZeeqn33N4jIRxbPECc,1879
+ocr_postprocess/extractors/label_anchor/regex_after_label.py,sha256=PTzOoj8MdXcy9iHZHgbqJ0C76ZdYHeKY4taSVY5vx6s,2802
+ocr_postprocess/extractors/label_anchor/text_until_next_label.py,sha256=jO7JIW7VQNSuhbCkAhDtV43dgyhk70HyCY6f_928-W4,2957
+ocr_postprocess/extractors/label_anchor/value_between_labels.py,sha256=LTUyExIAuhezjy9jTBUvvRDfHppb2bXI_kjvo4Ds20Q,2284
+ocr_postprocess/extractors/label_anchor/value_in_same_line.py,sha256=7aTKbNm0qoBQ86_ovYGEb6egqTHx8fpNhSDLdvcKd68,2078
+ocr_postprocess/extractors/pattern/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ocr_postprocess/extractors/pattern/cccd.py,sha256=g6gNwbJnVDN7gJtn3aaPGOPGzBSZPVc9WohlTrUYePU,2651
+ocr_postprocess/extractors/pattern/cmnd.py,sha256=mfETtPV9xVRzhmcOrN73BySoyEkVKv8z9OfPsxaq5ok,1150
+ocr_postprocess/extractors/pattern/currency_vnd.py,sha256=cFVE_6O4feOGwd961YxByvmVqg_NatBMT8wjvVlmn-8,1541
+ocr_postprocess/extractors/pattern/date.py,sha256=MSsR0vpYi_ElvaeUdOsfyEKE2ulw4mwe5sjBmwqqQqo,2906
+ocr_postprocess/extractors/pattern/email.py,sha256=u0qE31YsAWXhWpaHJbFQE4N1CWOsvXj_1Wnb5gxWEDY,1157
+ocr_postprocess/extractors/pattern/gender_vn.py,sha256=yWYGYmjH4PUyn87tcdl5RQt8f21ChG-EngJYfZd7fP8,1383
+ocr_postprocess/extractors/pattern/phone_vn.py,sha256=5quJ22uUsJySn0EBUvbdY3iuh8Pk8U1QA1E6OWn_YUY,1972
+ocr_postprocess/extractors/pattern/plate_vn.py,sha256=GXWdd2qlBDT_mOQUd-ZP25WLJ5mde5mQyti8Zn1IDpo,1284
+ocr_postprocess/extractors/pattern/tax_code.py,sha256=Ywd3fRT8Pjdu5CZDvoeFOArWyGQKbIpjEuXR2BmwcWw,1775
+ocr_postprocess/extractors/structured/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ocr_postprocess/extractors/structured/mrz_cccd.py,sha256=DAd-BIxW78Pqf3j3xhNVYp0Xrqzz5qQeKXxhaCC9OYc,3623
+ocr_postprocess/profiles/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ocr_postprocess/profiles/_generic.yml,sha256=oD73q5wnj76zhiK4CvMy8qxuhec1Sj-J-Rws8tPTs_M,161
+ocr_postprocess/profiles/cccd_2024.yml,sha256=pQagCWOzOJ-pHWKlNYr131FlNcOVfacvhZJt2tUGqmg,3568
+ocr_postprocess/profiles/dang_kiem.yml,sha256=QPryEckEkIohYkQeVuUsSh7Na6Z9uWOo45eCkO5HYec,2890
+ocr_postprocess/profiles/loader.py,sha256=pxS1R9UEMgOovhS9BEfmDQydt64oRFafUAxgbc5y2Cg,2108
+ocr_postprocess/profiles/matcher.py,sha256=VCqV72NMqITw8Y62quJut7ZxmRwC3sD_1kDo0a1TUKo,2092
+ocr_postprocess/profiles/schema.py,sha256=tUnYd5BfLMG1B9v9a7Qfa-jIoz6GwJcV_daAkkUvXLA,6157
+ocr_postprocess/renderer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ocr_postprocess/renderer/json_renderer.py,sha256=hR2L0Brs7QN5-GCgPLNsqk2ZBjcjkeCvFE6olVEuTII,1841
+ocr_postprocess/renderer/llm.py,sha256=PIog7ddLaShJDGGiDLLr_L7VITfAzGl0DyLubut0Oog,1350
+ocr_postprocess/renderer/markdown.py,sha256=fklOqrk3m2c8kyAmxDJFKZkpc49M18SUttZkr1CPu6k,6866
+ocr_postprocess-0.1.0.dist-info/METADATA,sha256=iVzgWPUxLNHI_hfZs2BKlB5fK5XlbsjBAKURm5u34Xw,4592
+ocr_postprocess-0.1.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+ocr_postprocess-0.1.0.dist-info/entry_points.txt,sha256=TzBHQMR05LYex2OIneKnqqyoM0sDGZGb03VLhH8RAds,50
+ocr_postprocess-0.1.0.dist-info/top_level.txt,sha256=EJBbBVsIAzSLT376rE4C9-wYGhR6P8OMw2117it7dz8,16
+ocr_postprocess-0.1.0.dist-info/RECORD,,

ocr_postprocess-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

ocr_postprocess-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+ocrpp = ocr_postprocess.cli:app

ocr_postprocess-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+ocr_postprocess