sohojpath 0.1.1__py3-none-any.whl

sohojpath/__init__.py

@@ -0,0 +1,6 @@
+"""Public API for :mod:`sohojpath`."""
+
+from ._version import __version__
+from .engine import BanglaPdfParser, OcrPage, OcrWord, ParserConfig
+
+__all__ = ["BanglaPdfParser", "OcrPage", "OcrWord", "ParserConfig", "__version__"]

sohojpath/__main__.py

@@ -0,0 +1,3 @@
+from .cli import main
+
+raise SystemExit(main())

sohojpath/_version.py

@@ -0,0 +1,3 @@
+"""Single source for Sohojpath's package version."""
+
+__version__ = "0.1.1"

sohojpath/cli.py

@@ -0,0 +1,100 @@
+"""Command-line interface for Sohojpath."""
+
+from __future__ import annotations
+
+import argparse
+import json
+import sys
+from pathlib import Path
+
+from ._version import __version__
+from .engine import BanglaPdfParser, ParserConfig
+
+
+def page_numbers(specification: str | None) -> list[int] | None:
+    if not specification:
+        return None
+    pages = set()
+    for part in specification.split(","):
+        bounds = part.strip().split("-", 1)
+        if len(bounds) == 1:
+            pages.add(int(bounds[0]))
+        else:
+            start, stop = map(int, bounds)
+            if start > stop:
+                raise ValueError(f"Invalid descending page range: {part}")
+            pages.update(range(start, stop + 1))
+    return sorted(pages)
+
+
+def configuration(args: argparse.Namespace) -> ParserConfig:
+    return ParserConfig(
+        language=args.language,
+        dpi=args.dpi,
+        page_segmentation_mode=args.psm,
+        minimum_confidence=args.minimum_confidence,
+        tesseract=args.tesseract,
+        tessdata=args.tessdata,
+        tesseract_timeout_seconds=args.timeout,
+    )
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(prog="sohojpath", description="Parse Bangla PDFs with OCR.")
+    parser.add_argument("--version", action="version", version=f"%(prog)s {__version__}")
+    shared = argparse.ArgumentParser(add_help=False)
+    shared.add_argument("--language", default="ben+eng")
+    shared.add_argument("--dpi", type=int, default=300)
+    shared.add_argument("--psm", type=int, default=6)
+    shared.add_argument("--minimum-confidence", type=float, default=0)
+    shared.add_argument("--tesseract", type=Path)
+    shared.add_argument("--tessdata", type=Path)
+    shared.add_argument(
+        "--timeout",
+        type=float,
+        default=120,
+        help="Maximum seconds for each Tesseract invocation (default: 120).",
+    )
+    commands = parser.add_subparsers(dest="command", required=True)
+    commands.add_parser("doctor", parents=[shared], help="Check Tesseract and language data.")
+    for name, help_text in (
+        ("text", "Extract normalized UTF-8 text."),
+        ("ocr", "Write page-level JSON Lines with word geometry."),
+    ):
+        command = commands.add_parser(name, parents=[shared], help=help_text)
+        command.add_argument("input", type=Path)
+        command.add_argument("--output", type=Path)
+        command.add_argument("--pages", help="One-based pages, e.g. 1,3-5")
+    return parser
+
+
+def main(argv: list[str] | None = None) -> int:
+    args = build_parser().parse_args(argv)
+    try:
+        engine = BanglaPdfParser(configuration(args))
+        if args.command == "doctor":
+            engine.validate()
+            print(f"Tesseract: {engine.tesseract}")
+            print(f"Languages: {', '.join(sorted(engine.installed_languages()))}")
+            return 0
+        pages = page_numbers(args.pages)
+        destination = (
+            args.output.open("w", encoding="utf-8", newline="\n") if args.output else sys.stdout
+        )
+        try:
+            for page in engine.parse(args.input, pages):
+                if args.command == "text":
+                    destination.write(page.text + "\n")
+                else:
+                    destination.write(json.dumps(page.as_dict(), ensure_ascii=False) + "\n")
+        finally:
+            if args.output:
+                destination.close()
+        return 0
+    except (OSError, RuntimeError, ValueError) as exc:
+        print(f"error: {exc}", file=sys.stderr)
+        return 2
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

sohojpath/engine.py

@@ -0,0 +1,222 @@
+"""Reusable, geometry-preserving Bengali PDF OCR engine for Sohojpath."""
+
+from __future__ import annotations
+
+import csv
+import io
+import math
+import os
+import shutil
+import subprocess
+import unicodedata
+from collections.abc import Iterable, Iterator
+from dataclasses import asdict, dataclass
+from pathlib import Path
+
+import pymupdf
+
+
+def normalize_text(value: str) -> str:
+    """Normalize Unicode without destroying Bengali spelling or word boundaries."""
+    return " ".join(unicodedata.normalize("NFC", value).split())
+
+
+@dataclass(frozen=True)
+class ParserConfig:
+    language: str = "ben+eng"
+    dpi: int = 300
+    page_segmentation_mode: int = 6
+    minimum_confidence: float = 0.0
+    tesseract: Path | None = None
+    tessdata: Path | None = None
+    tesseract_timeout_seconds: float = 120.0
+
+    def __post_init__(self) -> None:
+        languages = self.language.split("+")
+        if not languages or any(
+            not language.strip() or language != language.strip() for language in languages
+        ):
+            raise ValueError("language must contain one or more '+'-separated language codes")
+        if self.dpi <= 0:
+            raise ValueError("dpi must be greater than zero")
+        if not 0 <= self.page_segmentation_mode <= 13:
+            raise ValueError("page_segmentation_mode must be between 0 and 13")
+        if not math.isfinite(self.minimum_confidence):
+            raise ValueError("minimum_confidence must be finite")
+        if not math.isfinite(self.tesseract_timeout_seconds) or self.tesseract_timeout_seconds <= 0:
+            raise ValueError("tesseract_timeout_seconds must be a positive finite number")
+
+
+@dataclass(frozen=True)
+class OcrWord:
+    text: str
+    confidence: float
+    left: int
+    top: int
+    width: int
+    height: int
+    block: int
+    paragraph: int
+    line: int
+
+    def as_dict(self) -> dict[str, object]:
+        return asdict(self)
+
+
+@dataclass(frozen=True)
+class OcrPage:
+    source: str
+    page: int
+    width: int
+    height: int
+    dpi: int
+    text: str
+    words: tuple[OcrWord, ...]
+
+    def as_dict(self, *, include_words: bool = True) -> dict[str, object]:
+        result = {key: value for key, value in asdict(self).items() if key != "words"}
+        if include_words:
+            result["words"] = [word.as_dict() for word in self.words]
+        return result
+
+
+def find_tesseract(explicit: Path | None = None) -> Path:
+    discovered = shutil.which("tesseract")
+    candidates = [explicit, Path(discovered) if discovered else None]
+    if os.name == "nt":
+        candidates.append(Path(r"C:\Program Files\Tesseract-OCR\tesseract.exe"))
+    for candidate in candidates:
+        if candidate and candidate.is_file():
+            return candidate
+    raise FileNotFoundError("Tesseract was not found; install it or pass tesseract=Path(...)")
+
+
+class BanglaPdfParser:
+    """Render PDF pages and return Bengali OCR text with word geometry."""
+
+    def __init__(self, config: ParserConfig | None = None):
+        self.config = config or ParserConfig()
+        self.tesseract = find_tesseract(self.config.tesseract)
+
+    def installed_languages(self) -> set[str]:
+        command = [str(self.tesseract), "--list-langs"]
+        if self.config.tessdata:
+            command.extend(("--tessdata-dir", str(self.config.tessdata.resolve())))
+        result = self._run_tesseract(command)
+        if result.returncode:
+            raise RuntimeError(result.stderr.decode("utf-8", errors="replace"))
+        lines = result.stdout.decode("utf-8-sig", errors="replace").splitlines()
+        return {line.strip() for line in lines[1:] if line.strip()}
+
+    def validate(self) -> None:
+        requested = set(self.config.language.split("+"))
+        missing = requested - self.installed_languages()
+        if missing:
+            raise RuntimeError(f"Missing Tesseract language data: {', '.join(sorted(missing))}")
+
+    def parse(self, pdf: str | Path, pages: Iterable[int] | None = None) -> Iterator[OcrPage]:
+        path = Path(pdf)
+        if not path.is_file():
+            raise FileNotFoundError(path)
+        self.validate()
+        try:
+            with pymupdf.open(path) as document:  # type: ignore[no-untyped-call]
+                selected = range(1, document.page_count + 1) if pages is None else pages
+                for page_number in selected:
+                    if not isinstance(page_number, int):
+                        raise ValueError(f"Page number must be an integer: {page_number!r}")
+                    if not 1 <= page_number <= document.page_count:
+                        raise ValueError(f"Page {page_number} is outside 1-{document.page_count}")
+                    page = document[page_number - 1]
+                    pixmap = page.get_pixmap(dpi=self.config.dpi, alpha=False)
+                    words = self._ocr_png(pixmap.tobytes("png"))
+                    yield OcrPage(
+                        str(path),
+                        page_number,
+                        pixmap.width,
+                        pixmap.height,
+                        self.config.dpi,
+                        self._reading_order_text(words),
+                        tuple(words),
+                    )
+        except (pymupdf.FileDataError, pymupdf.FileNotFoundError) as exc:
+            raise RuntimeError(f"Could not open PDF {path}: {exc}") from exc
+
+    def _ocr_png(self, png: bytes) -> list[OcrWord]:
+        command = [str(self.tesseract), "stdin", "stdout"]
+        if self.config.tessdata:
+            command.extend(("--tessdata-dir", str(self.config.tessdata.resolve())))
+        command.extend(
+            (
+                "-l",
+                self.config.language,
+                "--psm",
+                str(self.config.page_segmentation_mode),
+                "-c",
+                "tessedit_create_tsv=1",
+            )
+        )
+        result = self._run_tesseract(command, input_data=png)
+        if result.returncode:
+            raise RuntimeError(result.stderr.decode("utf-8", errors="replace"))
+        output = []
+        reader = csv.DictReader(
+            io.StringIO(result.stdout.decode("utf-8-sig", errors="replace")), delimiter="\t"
+        )
+        for row in reader:
+            text = normalize_text(row.get("text", ""))
+            try:
+                confidence = float(row.get("conf", "-1"))
+            except ValueError:
+                confidence = -1
+            if row.get("level") != "5" or not text or confidence < self.config.minimum_confidence:
+                continue
+            try:
+                output.append(
+                    OcrWord(
+                        text,
+                        confidence,
+                        int(row["left"]),
+                        int(row["top"]),
+                        int(row["width"]),
+                        int(row["height"]),
+                        int(row["block_num"]),
+                        int(row["par_num"]),
+                        int(row["line_num"]),
+                    )
+                )
+            except (KeyError, TypeError, ValueError) as exc:
+                raise RuntimeError("Tesseract returned malformed TSV word data") from exc
+        return output
+
+    def _run_tesseract(
+        self, command: list[str], *, input_data: bytes | None = None
+    ) -> subprocess.CompletedProcess[bytes]:
+        try:
+            return subprocess.run(
+                command,
+                input=input_data,
+                capture_output=True,
+                check=False,
+                timeout=self.config.tesseract_timeout_seconds,
+            )
+        except subprocess.TimeoutExpired as exc:
+            raise RuntimeError(
+                f"Tesseract timed out after {self.config.tesseract_timeout_seconds:g} seconds"
+            ) from exc
+        except OSError as exc:
+            raise RuntimeError(f"Could not run Tesseract: {exc}") from exc
+
+    @staticmethod
+    def _reading_order_text(words: list[OcrWord]) -> str:
+        lines: dict[tuple[int, int, int], list[OcrWord]] = {}
+        for word in words:
+            lines.setdefault((word.block, word.paragraph, word.line), []).append(word)
+        ordered = sorted(
+            lines.values(),
+            key=lambda line: (min(word.top for word in line), min(word.left for word in line)),
+        )
+        return "\n".join(
+            " ".join(word.text for word in sorted(line, key=lambda item: item.left))
+            for line in ordered
+        )

sohojpath/py.typed

@@ -0,0 +1 @@
+

sohojpath-0.1.1.dist-info/METADATA

@@ -0,0 +1,176 @@
+Metadata-Version: 2.4
+Name: sohojpath
+Version: 0.1.1
+Summary: Geometry-preserving Bengali OCR for PDF documents
+Author: Anindya
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/Anindyakafka/sohojpath
+Project-URL: Documentation, https://github.com/Anindyakafka/sohojpath#readme
+Project-URL: Repository, https://github.com/Anindyakafka/sohojpath
+Project-URL: Issues, https://github.com/Anindyakafka/sohojpath/issues
+Keywords: bangla,bengali,ocr,pdf,tesseract
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Natural Language :: Bengali
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Text Processing :: Linguistic
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: PyMuPDF>=1.24
+Provides-Extra: dev
+Requires-Dist: build>=1.2; extra == "dev"
+Requires-Dist: coverage[toml]>=7.6; extra == "dev"
+Requires-Dist: mypy>=1.13; extra == "dev"
+Requires-Dist: ruff>=0.8; extra == "dev"
+Requires-Dist: twine>=6.0; extra == "dev"
+Dynamic: license-file
+
+# Sohojpath
+
+[![CI](https://github.com/Anindyakafka/sohojpath/actions/workflows/ci.yml/badge.svg)](https://github.com/Anindyakafka/sohojpath/actions/workflows/ci.yml)
+[![PyPI](https://img.shields.io/pypi/v/sohojpath.svg)](https://pypi.org/project/sohojpath/)
+[![Python](https://img.shields.io/pypi/pyversions/sohojpath.svg)](https://pypi.org/project/sohojpath/)
+[![License](https://img.shields.io/github/license/Anindyakafka/sohojpath)](LICENSE)
+
+Sohojpath is a Python library and command-line tool for geometry-preserving Bengali PDF
+OCR. It extracts normalized Unicode text while retaining each word's bounding box,
+Tesseract line identifiers, and confidence score for table extraction, document analysis,
+and human review.
+
+> Sohojpath is currently alpha software. OCR output is not ground truth; validate critical
+> fields and retain a manual-review path.
+
+## Features
+
+- Bengali or bilingual OCR through Tesseract (`ben`, `ben+eng`, or another installed set)
+- Normalized UTF-8 plain-text output
+- Page-level JSON Lines with word coordinates and confidence
+- One-based page selection such as `1,3-5`
+- Python API and `sohojpath` CLI
+- Explicit language-data diagnostics
+- Type information through `py.typed`
+
+## Requirements and installation
+
+Sohojpath requires Python 3.10 or newer and Tesseract OCR with Bengali language data.
+
+```powershell
+# Windows
+winget install UB-Mannheim.TesseractOCR
+```
+
+```bash
+# Ubuntu/Debian
+sudo apt install tesseract-ocr tesseract-ocr-ben
+
+# macOS
+brew install tesseract tesseract-lang
+```
+
+Install Sohojpath:
+
+```bash
+python -m pip install sohojpath
+```
+
+For development from a clone:
+
+```bash
+python -m pip install -e ".[dev]"
+```
+
+## Command line
+
+```bash
+# Check Tesseract and language availability
+sohojpath doctor
+
+# Extract normalized text
+sohojpath text document.pdf --pages 1-3 --output document.txt
+
+# Extract page-level JSON Lines with word geometry
+sohojpath ocr document.pdf --pages 1-3 --output document.jsonl
+```
+
+Useful options:
+
+```text
+--language ben+eng       Tesseract languages
+--dpi 300                Rendering resolution
+--psm 6                  Tesseract page-segmentation mode
+--minimum-confidence 40  Exclude lower-confidence words
+--tesseract PATH         Explicit Tesseract executable
+--tessdata PATH          Explicit language-data directory
+--timeout SECONDS        Maximum time for each Tesseract invocation
+```
+
+Run `sohojpath COMMAND --help` for the complete command reference.
+
+## Python API
+
+```python
+from sohojpath import BanglaPdfParser, ParserConfig
+
+parser = BanglaPdfParser(ParserConfig(language="ben+eng", dpi=300))
+
+for page in parser.parse("document.pdf", pages=[1, 2]):
+    print(page.page, page.text)
+    for word in page.words:
+        print(word.text, word.confidence, word.left, word.top)
+```
+
+If language files are outside Tesseract's default location, pass
+`ParserConfig(tessdata=Path("path/to/tessdata"))`.
+
+## Structured output
+
+The `ocr` command emits JSON Lines so large PDFs can be processed incrementally. Each page
+contains its source, one-based page number, DPI, pixel dimensions, normalized text, and
+words with confidence, bounding box, block, paragraph, and line identifiers.
+
+Coordinates are integer pixels in the page image rendered at the requested DPI. Pages are
+emitted in the requested order; words are emitted in Tesseract's TSV order. The synthesized
+page text groups words by Tesseract block, paragraph, and line identifiers and orders them
+top-to-bottom, then left-to-right.
+
+The JSONL structure is considered provisional during the 0.x series. Incompatible schema
+changes will be called out in the changelog.
+
+## Scope and accuracy
+
+Version 0.1 provides a reusable OCR and geometry layer. Document-specific schemas—such as
+electoral rolls, forms, registers, or fixed-column tables—should be implemented as opt-in
+profiles on top of the word geometry API.
+
+Applications handling names, identity numbers, legal records, or other sensitive fields
+should preserve source documents, confidence values, validation results, and review
+decisions.
+
+## Development
+
+```bash
+python -m pip install -e ".[dev]"
+python -m ruff format --check .
+python -m ruff check .
+python -m mypy
+python -m coverage run -m unittest discover -s tests -v
+python -m coverage report
+python -m build
+python -m twine check dist/*
+```
+
+The Python API raises `ValueError` for invalid configuration or page selection,
+`FileNotFoundError` for a missing input or Tesseract executable, and `RuntimeError` for PDF,
+language-data, malformed OCR output, timeout, and Tesseract execution failures. The CLI
+reports these failures on standard error and exits with status 2.
+
+See [CONTRIBUTING.md](CONTRIBUTING.md), [SUPPORT.md](SUPPORT.md), and
+[SECURITY.md](SECURITY.md).
+
+## License
+
+Licensed under the [Apache License 2.0](LICENSE).

sohojpath-0.1.1.dist-info/RECORD

@@ -0,0 +1,12 @@
+sohojpath/__init__.py,sha256=jmvDFH6nxpsiuP8j-BN5j-_jmJnhabVGqg6SNoW6_Cg,226
+sohojpath/__main__.py,sha256=k1ocEWawweo1qCJWNFAAvyxz3tcY13dzvCenHszij30,48
+sohojpath/_version.py,sha256=9wjLWpHBHadof5BohxB-grsqe8Zh8TkVEBOFG509w_w,76
+sohojpath/cli.py,sha256=cTyFEA1trfThZ3gL_w6JtGRmr3rVDuPp0OMjyEDvcpc,3605
+sohojpath/engine.py,sha256=39h-Y1GeaPe7Nl_iMwFju8Rs0kWmqJ9V4Lh9ccv6XHI,8439
+sohojpath/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+sohojpath-0.1.1.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+sohojpath-0.1.1.dist-info/METADATA,sha256=PZ-huDSbf5wkbHNrtjf2VJnsTpMACTkVY7XIRIJ4VWc,6027
+sohojpath-0.1.1.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
+sohojpath-0.1.1.dist-info/entry_points.txt,sha256=FjPZgJlQrl7cnkK6uok-rGELd2u8caCkyKWJxvZbFZ0,49
+sohojpath-0.1.1.dist-info/top_level.txt,sha256=ekOeba7-xUicTYaO_owRjO7crM5pQwTibyvCGAfUYeI,10
+sohojpath-0.1.1.dist-info/RECORD,,

sohojpath-0.1.1.dist-info/WHEEL

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

sohojpath-0.1.1.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+sohojpath = sohojpath.cli:main

sohojpath-0.1.1.dist-info/licenses/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

sohojpath-0.1.1.dist-info/top_level.txt

@@ -0,0 +1 @@
+sohojpath