ugarit-texts 0.1.0__py3-none-any.whl

ugarit/__init__.py

@@ -0,0 +1,77 @@
+"""Browse the locally supplied Ugaritic Baal Cycle extraction."""
+from dataclasses import dataclass
+from pathlib import Path
+import re
+
+DEFAULT_SOURCE = Path.home() / "Documents" / "Ugaritic Baal Cycle Volumes I and II.md"
+_HEADING = re.compile(r"^#{1,3} .+$", re.MULTILINE)
+_COLUMN = re.compile(r"^## (?:(?:CAT|KTU) )?(1\.[1-4]) (I{1,3}|IV|V|VI{0,3})(?: and CAT 1\.8)?$", re.MULTILINE)
+_PAGE = re.compile(r"^### PDF page (\d+)\s*\n\s*```text\s*\n(.*?)\n```", re.MULTILINE | re.DOTALL)
+
+@dataclass(frozen=True)
+class Page:
+    volume: int
+    number: int
+    text: str
+
+@dataclass(frozen=True)
+class Section:
+    tablet: str
+    column: str
+    volume: int
+    text: str
+
+class Corpus:
+    def __init__(self, source=DEFAULT_SOURCE):
+        self.source = Path(source)
+        self._text = self.source.read_text(encoding="utf-8-sig")
+        marker = self._text.find("\n# Volume II\n")
+        if marker < 0:
+            raise ValueError("Source is missing the Volume II heading")
+        self._volumes = {1: self._text[:marker], 2: self._text[marker:]}
+
+    def tablets(self):
+        """Return tablet identifiers represented by column sections."""
+        return tuple(dict.fromkeys(s.tablet for s in self.sections()))
+
+    def sections(self, tablet=None):
+        """Return sections in source order; each includes commentary and page markers."""
+        result = []
+        for volume, text in self._volumes.items():
+            matches = list(_COLUMN.finditer(text))
+            for match in matches:
+                end = _HEADING.search(text, match.end())
+                # Page headings occur within sections; stop only at the next level-2 heading.
+                next_section = re.search(r"^## ", text[match.end():], re.MULTILINE)
+                stop = match.end() + next_section.start() if next_section else len(text)
+                item = Section(match.group(1), match.group(2), volume, text[match.end():stop].strip())
+                if tablet is None or item.tablet == str(tablet).removeprefix("KTU ").removeprefix("CAT "):
+                    result.append(item)
+        return tuple(result)
+
+    def get(self, tablet, column):
+        """Get a tablet column, e.g. get('1.3', 'IV'); raises KeyError if absent."""
+        for section in self.sections(tablet):
+            if section.column == str(column).upper():
+                return section
+        raise KeyError(f"No section for {tablet} column {column}")
+
+    def pages(self, volume=None):
+        """Return extracted PDF pages, optionally restricted to volume 1 or 2."""
+        if volume is not None and volume not in self._volumes:
+            raise ValueError("volume must be 1 or 2")
+        volumes = self._volumes.items() if volume is None else [(volume, self._volumes[volume])]
+        return tuple(Page(v, int(m.group(1)), m.group(2)) for v, text in volumes for m in _PAGE.finditer(text))
+
+    def page(self, volume, number):
+        for page in self.pages(volume):
+            if page.number == number:
+                return page
+        raise KeyError(f"No PDF page {number} in volume {volume}")
+
+    def search(self, query, volume=None):
+        """Return pages containing a case-insensitive literal query."""
+        if not query:
+            raise ValueError("query must not be empty")
+        needle = query.casefold()
+        return tuple(page for page in self.pages(volume) if needle in page.text.casefold())

ugarit_texts-0.1.0.dist-info/METADATA

@@ -0,0 +1,95 @@
+Metadata-Version: 2.4
+Name: ugarit-texts
+Version: 0.1.0
+Summary: Browse a local Markdown extraction of the Ugaritic Baal Cycle
+License: MIT License
+        
+        Copyright (c) 2026 ugarit-texts contributors
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Keywords: ugaritic,baal cycle,ancient texts
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Text Processing
+Classifier: Topic :: Religion
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file
+
+# ugarit-texts
+
+Browse a locally supplied Markdown extraction of *The Ugaritic Baal Cycle*, Volumes I and II, using Python. Look up tablet columns, retrieve PDF pages, and search page text. Python 3.9 or later is required; there are no runtime dependencies.
+
+## Install
+
+```sh
+python -m pip install ugarit-texts
+```
+
+The package contains code only. It does **not** include the books or a text corpus. You must supply the matching Markdown extraction yourself. By default, `Corpus()` looks for `Ugaritic Baal Cycle Volumes I and II.md` in your home directory's `Documents` folder. Alternatively, pass a path:
+
+```python
+from ugarit import Corpus
+
+corpus = Corpus(r"C:\path\to\Ugaritic Baal Cycle Volumes I and II.md")
+```
+
+The input must have the volume, section, PDF-page and fenced text headings used by that extraction; this is not a general parser for arbitrary Ugaritic editions. A missing file raises `FileNotFoundError`.
+
+## Browse tablet columns
+
+```python
+from ugarit import Corpus
+
+corpus = Corpus()
+print(corpus.tablets())                 # ('1.1', '1.2', '1.3', '1.4')
+section = corpus.get('KTU 1.3', 'IV') # CAT prefix also accepted
+print(section.tablet, section.column, section.volume)
+print(section.text)
+
+for section in corpus.sections('1.2'):
+    print(section.column, section.volume)
+```
+
+`sections()` returns all indexed sections in source order; pass a tablet identifier to filter them. `get(tablet, column)` returns a `Section` with `tablet`, `column`, `volume`, and `text` attributes, or raises `KeyError`. Roman column numbers are case-insensitive.
+
+Sections are taken from the extraction's headings. They include commentary, notes and page markers, and may include material outside the named column. They are not clean verse-level transcriptions or isolated translations.
+
+## Retrieve and search pages
+
+```python
+page = corpus.page(1, 2)          # volume 1, PDF page 2
+print(page.text)
+
+for page in corpus.search('Baal', volume=2):
+    print(page.volume, page.number)
+
+all_pages = corpus.pages()        # or corpus.pages(volume=1)
+```
+
+Page numbers refer to PDF pages, not printed book pages. Search performs a case-insensitive literal substring match and returns matching `Page` objects with `volume`, `number`, and `text` attributes. An empty query or invalid volume raises `ValueError`; a missing page raises `KeyError`.
+
+## Scope and source
+
+The source describes Mark S. Smith, *The Ugaritic Baal Cycle*, Volume I (Brill, 1994), covering KTU 1.1–1.2; and Smith and Wayne T. Pitard, Volume II (Brill, 2009), covering KTU/CAT 1.3–1.4. KTU 1.5–1.6 and the wider Ugaritic corpus are not included. The Markdown is a mechanical PDF extraction with OCR errors, disrupted columns, missing images, and section headings placed at page boundaries. Consult the original editions when accuracy matters.
+
+## License
+
+The library code is available under the [MIT License](LICENSE). The ancient Ugaritic works are distinct from modern editions, translations and commentaries. The supplied Brill edition is not licensed here and is not distributed with this package; no CC BY license is claimed for it. Obtain and use your source copy under its applicable rights.

ugarit_texts-0.1.0.dist-info/RECORD

@@ -0,0 +1,6 @@
+ugarit/__init__.py,sha256=QCVWX7BxzfPQTxL-LJjDedEeHXcxwEC0QCVSAJxhqtc,3402
+ugarit_texts-0.1.0.dist-info/licenses/LICENSE,sha256=wTHwXVpF7vJfXi8wQC49SyoHad8nCtgJtMj1y7lwHLU,1086
+ugarit_texts-0.1.0.dist-info/METADATA,sha256=LKetWl0gjDDXX9nJwAGRCvY-JycbAlZTPerwQGd3ry4,4936
+ugarit_texts-0.1.0.dist-info/WHEEL,sha256=YLJXdYXQ2FQ0Uqn2J-6iEIC-3iOey8lH3xCtvFLkd8Q,91
+ugarit_texts-0.1.0.dist-info/top_level.txt,sha256=J4FRNHuD_wP4Sht_Byw4sJreoTQio8aVU1ASPCxW7gM,7
+ugarit_texts-0.1.0.dist-info/RECORD,,

ugarit_texts-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (81.0.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

ugarit_texts-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 ugarit-texts contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

ugarit_texts-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+ugarit