refren 0.1.0__tar.gz

refren-0.1.0/.gitignore

@@ -0,0 +1,207 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

refren-0.1.0/.python-version

@@ -0,0 +1 @@
+3.12

refren-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 ljbuturovic
+
+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.

refren-0.1.0/PKG-INFO

@@ -0,0 +1,26 @@
+Metadata-Version: 2.4
+Name: refren
+Version: 0.1.0
+Summary: Scientific manuscript PDF file renamer
+License: MIT
+License-File: LICENSE
+Requires-Python: >=3.12
+Requires-Dist: anthropic>=0.86.0
+Requires-Dist: pdfplumber>=0.11
+Description-Content-Type: text/markdown
+
+# refren: scientific manuscript PDF file renamer
+
+```bash
+$ ./refren.py 1758-2946-6-10.pdf 
+  (direct parsing incomplete — calling Claude API...)
+  First author last name : Krstajic
+  Second author last name: Buturovic
+  Journal                : Journal of Cheminformatics -> J Cheminform
+  Year                   : 2014
+
+  1758-2946-6-10.pdf  ->  Krstajic_Buturovic_JCheminform_2014.pdf
+Rename? [y/N] y
+Renamed to: Krstajic_Buturovic_JCheminform_2014.pdf
+```
+

refren-0.1.0/README.md

@@ -0,0 +1,15 @@
+# refren: scientific manuscript PDF file renamer
+
+```bash
+$ ./refren.py 1758-2946-6-10.pdf 
+  (direct parsing incomplete — calling Claude API...)
+  First author last name : Krstajic
+  Second author last name: Buturovic
+  Journal                : Journal of Cheminformatics -> J Cheminform
+  Year                   : 2014
+
+  1758-2946-6-10.pdf  ->  Krstajic_Buturovic_JCheminform_2014.pdf
+Rename? [y/N] y
+Renamed to: Krstajic_Buturovic_JCheminform_2014.pdf
+```
+

refren-0.1.0/main.py

@@ -0,0 +1,6 @@
+def main():
+    print("Hello from refren!")
+
+
+if __name__ == "__main__":
+    main()

refren-0.1.0/pyproject.toml

@@ -0,0 +1,25 @@
+[project]
+name = "refren"
+version = "0.1.0"
+description = "Scientific manuscript PDF file renamer"
+readme = "README.md"
+requires-python = ">=3.12"
+license = { text = "MIT" }
+dependencies = [
+    "anthropic>=0.86.0",
+    "pdfplumber>=0.11",
+]
+
+[project.scripts]
+refren = "refren:main"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[dependency-groups]
+dev = [
+    "build>=1.4.2",
+    "hatchling>=1.29.0",
+    "twine>=6.2.0",
+]

refren-0.1.0/refren.py

@@ -0,0 +1,247 @@
+#!/usr/bin/env python3
+"""
+Rename a scientific PDF as: FirstAuthorLastName_SecondAuthorLastName_JournalAbbrev_Year.pdf
+Usage: ./renamer.py <pdf_file>
+"""
+
+import re
+import sys
+from pathlib import Path
+
+import anthropic
+import pdfplumber
+from pydantic import BaseModel
+
+
+# --- Journal abbreviation lookup ---
+JOURNAL_ABBREVIATIONS = {
+    "diagnostic and prognostic research": "DiagProgRes",
+    "nature medicine": "NatMed",
+    "nature communications": "NatCommun",
+    "nature": "Nature",
+    "science": "Science",
+    "cell": "Cell",
+    "the lancet": "Lancet",
+    "lancet": "Lancet",
+    "new england journal of medicine": "NEJM",
+    "n engl j med": "NEJM",
+    "jama": "JAMA",
+    "bmj": "BMJ",
+    "annals of internal medicine": "AnnInternMed",
+    "plos medicine": "PLoSMed",
+    "plos one": "PLoSOne",
+    "plos biology": "PLoSBiol",
+    "plos computational biology": "PLoSComputBiol",
+    "bioinformatics": "Bioinformatics",
+    "nucleic acids research": "NucleicAcidsRes",
+    "genome biology": "GenomeBiol",
+    "genome research": "GenomeRes",
+    "molecular cell": "MolCell",
+    "cell reports": "CellRep",
+    "cell systems": "CellSyst",
+    "elife": "eLife",
+    "journal of clinical oncology": "JClinOncol",
+    "cancer research": "CancerRes",
+    "cancer cell": "CancerCell",
+    "clinical cancer research": "ClinCancerRes",
+    "journal of the american medical informatics association": "JAMIA",
+    "npj digital medicine": "NPJDigitMed",
+    "artificial intelligence in medicine": "ArtifIntellMed",
+    "medical image analysis": "MedImageAnal",
+    "radiology": "Radiology",
+    "european radiology": "EurRadiol",
+    "circulation": "Circulation",
+    "european heart journal": "EurHeartJ",
+    "journal of the american college of cardiology": "JACC",
+    "diabetes care": "DiabetesCare",
+    "statistics in medicine": "StatMed",
+    "biometrics": "Biometrics",
+    "american journal of epidemiology": "AmJEpidemiol",
+    "epidemiology": "Epidemiology",
+    "international journal of epidemiology": "IntJEpidemiol",
+    "brain": "Brain",
+    "journal of neurology": "JNeurol",
+    "neurology": "Neurology",
+    "gut": "Gut",
+}
+
+
+def abbreviate_journal(full_name: str) -> str:
+    """Return a known abbreviation or derive a CamelCase abbreviation from the title."""
+    lower = full_name.lower().strip()
+    for key, abbr in JOURNAL_ABBREVIATIONS.items():
+        if key in lower:
+            return abbr
+    stop = {"a", "an", "the", "of", "in", "on", "and", "for", "to", "with", "&"}
+    words = re.sub(r"[^\w\s]", "", full_name).split()
+    return "".join(w.capitalize() for w in words if w.lower() not in stop) or "UnknownJournal"
+
+
+def extract_last_name(name: str) -> str:
+    """Return the last name from a full author name string (final word only)."""
+    name = name.strip().rstrip(",*0123456789† ")
+    parts = name.split()
+    return parts[-1] if parts else name
+
+
+def parse_authors_and_year(text: str):
+    """
+    Extract (first_author_last, second_author_last, year) from first-page text.
+    Returns (first, second, year) — any may be None if not found.
+    """
+    year = None
+    year_match = re.search(r"\b(20\d{2}|19\d{2})\b", text)
+    if year_match:
+        year = year_match.group(1)
+
+    first, second = None, None
+
+    # Pattern 1: "Surname et al." header
+    et_al_match = re.search(r"([A-Z][a-z]+(?:\s+[a-z]+)*)\s+et al\.", text)
+    if et_al_match:
+        first = et_al_match.group(1).strip()
+
+    # Pattern 2: full author line — comma-separated "Firstname Lastname, ..."
+    author_line_pattern = re.compile(
+        r"([A-Z][a-z]+(?:\s+[a-z]+)*\s+[A-Z][a-zA-Z\-]+[0-9†*,]*"
+        r"(?:\s*,\s*[A-Z][a-z]+(?:\s+[a-z]+)*\s+[A-Z][a-zA-Z\-]+[0-9†*,]*){1,})"
+    )
+    for match in author_line_pattern.finditer(text):
+        candidate = match.group(0)
+        raw_authors = [a.strip() for a in re.split(r",\s*", candidate) if a.strip()]
+        if len(raw_authors) >= 2:
+            last_names = [extract_last_name(a) for a in raw_authors]
+            if not first:
+                first = last_names[0]
+            second = last_names[1]
+            break
+
+    return first, second, year
+
+
+def extract_journal(text: str) -> str | None:
+    """Try to find the journal name from the first-page text."""
+    lower = text.lower()
+    for key in JOURNAL_ABBREVIATIONS:
+        if key in lower:
+            idx = lower.find(key)
+            return text[idx: idx + len(key)]
+    patterns = [
+        r"(?:published in|journal)[:\s]+([A-Z][^\n]+)",
+        r"https?://doi\.org/[^\s]+\s+([A-Z][A-Za-z &]+)\n",
+    ]
+    for pat in patterns:
+        m = re.search(pat, text, re.IGNORECASE)
+        if m:
+            return m.group(1).strip()
+    return None
+
+
+def sanitize(s: str) -> str:
+    """Remove characters unsafe for filenames."""
+    return re.sub(r"[^\w]", "", s)
+
+
+# --- Claude API fallback ---
+
+class PaperMetadata(BaseModel):
+    first_author_last_name: str
+    second_author_last_name: str
+    journal_full_name: str
+    journal_abbreviation: str
+    year: str
+
+
+def extract_via_llm(text: str, metadata: dict | None = None) -> PaperMetadata:
+    """Use Claude to extract paper metadata from first-page text."""
+    print("  (direct parsing incomplete — calling Claude API...)")
+    client = anthropic.Anthropic()
+    response = client.messages.parse(
+        model="claude-opus-4-6",
+        max_tokens=512,
+        system=(
+            "You are a scientific literature assistant. "
+            "Extract bibliographic metadata from the first page of a scientific paper. "
+            "For journal_abbreviation, use the standard ISO/NLM abbreviation (e.g. 'Circulation', "
+            "'N Engl J Med', 'JAMA', 'Nat Med'). "
+            "Return only last names for authors (no initials, no titles, no credentials)."
+        ),
+        messages=[{
+            "role": "user",
+            "content": (
+                "Extract the metadata from this scientific paper.\n\n"
+                + (f"PDF metadata: {metadata}\n\n" if metadata else "")
+                + f"First page text:\n{text[:4000]}"
+            ),
+        }],
+        output_format=PaperMetadata,
+    )
+    return response.parsed_output
+
+
+def rename_pdf(pdf_path: str):
+    path = Path(pdf_path)
+    if not path.exists():
+        print(f"Error: file not found: {pdf_path}")
+        sys.exit(1)
+    if path.suffix.lower() != ".pdf":
+        print(f"Error: not a PDF file: {pdf_path}")
+        sys.exit(1)
+
+    with pdfplumber.open(path) as pdf:
+        metadata = pdf.metadata or {}
+        first_page_text = pdf.pages[0].extract_text() or ""
+        if len(first_page_text) < 200 and len(pdf.pages) > 1:
+            first_page_text += "\n" + (pdf.pages[1].extract_text() or "")
+
+    first, second, year = parse_authors_and_year(first_page_text)
+    journal_full = extract_journal(first_page_text)
+    journal_abbr = abbreviate_journal(journal_full) if journal_full else None
+
+    # Try to extract year from PDF metadata if not found in text
+    if not year:
+        meta_str = " ".join(str(v) for v in metadata.values())
+        m = re.search(r"\b(20\d{2}|19\d{2})\b", meta_str)
+        if m:
+            year = m.group(1)
+
+    missing = [label for label, val in [
+        ("first author", first), ("second author", second),
+        ("year", year), ("journal", journal_full),
+    ] if not val]
+
+    if missing:
+        # When LLM is needed, trust it for all fields — regex results may also be wrong
+        meta = extract_via_llm(first_page_text, metadata)
+        first = meta.first_author_last_name
+        second = meta.second_author_last_name
+        year = meta.year
+        journal_full = meta.journal_full_name
+        journal_abbr = meta.journal_abbreviation
+
+    print(f"  First author last name : {first}")
+    print(f"  Second author last name: {second}")
+    print(f"  Journal                : {journal_full} -> {journal_abbr}")
+    print(f"  Year                   : {year}")
+
+    new_name = f"{sanitize(first)}_{sanitize(second)}_{sanitize(journal_abbr)}_{sanitize(year)}.pdf"
+    new_path = path.parent / new_name
+
+    print(f"\n  {path.name}  ->  {new_name}")
+    confirm = input("Rename? [y/N] ").strip().lower()
+    if confirm == "y":
+        path.rename(new_path)
+        print(f"Renamed to: {new_path}")
+    else:
+        print("Aborted.")
+
+
+def main():
+    if len(sys.argv) != 2:
+        print("Usage: ./renamer.py <pdf_file>")
+        sys.exit(1)
+    rename_pdf(sys.argv[1])
+
+
+if __name__ == "__main__":
+    main()

refren-0.1.0/requirements.txt

@@ -0,0 +1,137 @@
+# This file was autogenerated by uv via the following command:
+#    uv export --format requirements-txt --no-hashes -o requirements.txt
+-e .
+annotated-types==0.7.0
+    # via pydantic
+anthropic==0.86.0
+    # via refren
+anyio==4.13.0
+    # via
+    #   anthropic
+    #   httpx
+build==1.4.2
+certifi==2026.2.25
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+cffi==2.0.0 ; platform_python_implementation != 'PyPy'
+    # via cryptography
+charset-normalizer==3.4.6
+    # via
+    #   pdfminer-six
+    #   requests
+colorama==0.4.6 ; os_name == 'nt'
+    # via build
+cryptography==46.0.6
+    # via
+    #   pdfminer-six
+    #   secretstorage
+distro==1.9.0
+    # via anthropic
+docstring-parser==0.17.0
+    # via anthropic
+docutils==0.22.4
+    # via readme-renderer
+h11==0.16.0
+    # via httpcore
+hatchling==1.29.0
+httpcore==1.0.9
+    # via httpx
+httpx==0.28.1
+    # via anthropic
+id==1.6.1
+    # via twine
+idna==3.11
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+jaraco-classes==3.4.0 ; platform_machine != 'ppc64le' and platform_machine != 's390x'
+    # via keyring
+jaraco-context==6.1.2 ; platform_machine != 'ppc64le' and platform_machine != 's390x'
+    # via keyring
+jaraco-functools==4.4.0 ; platform_machine != 'ppc64le' and platform_machine != 's390x'
+    # via keyring
+jeepney==0.9.0 ; platform_machine != 'ppc64le' and platform_machine != 's390x' and sys_platform == 'linux'
+    # via
+    #   keyring
+    #   secretstorage
+jiter==0.13.0
+    # via anthropic
+keyring==25.7.0 ; platform_machine != 'ppc64le' and platform_machine != 's390x'
+    # via twine
+markdown-it-py==4.0.0
+    # via rich
+mdurl==0.1.2
+    # via markdown-it-py
+more-itertools==10.8.0 ; platform_machine != 'ppc64le' and platform_machine != 's390x'
+    # via
+    #   jaraco-classes
+    #   jaraco-functools
+nh3==0.3.4
+    # via readme-renderer
+packaging==26.0
+    # via
+    #   build
+    #   hatchling
+    #   twine
+pathspec==1.0.4
+    # via hatchling
+pdfminer-six==20251230
+    # via pdfplumber
+pdfplumber==0.11.9
+    # via refren
+pillow==12.1.1
+    # via pdfplumber
+pluggy==1.6.0
+    # via hatchling
+pycparser==3.0 ; implementation_name != 'PyPy' and platform_python_implementation != 'PyPy'
+    # via cffi
+pydantic==2.12.5
+    # via anthropic
+pydantic-core==2.41.5
+    # via pydantic
+pygments==2.19.2
+    # via
+    #   readme-renderer
+    #   rich
+pypdfium2==5.6.0
+    # via pdfplumber
+pyproject-hooks==1.2.0
+    # via build
+pywin32-ctypes==0.2.3 ; platform_machine != 'ppc64le' and platform_machine != 's390x' and sys_platform == 'win32'
+    # via keyring
+readme-renderer==44.0
+    # via twine
+requests==2.33.0
+    # via
+    #   requests-toolbelt
+    #   twine
+requests-toolbelt==1.0.0
+    # via twine
+rfc3986==2.0.0
+    # via twine
+rich==14.3.3
+    # via twine
+secretstorage==3.5.0 ; platform_machine != 'ppc64le' and platform_machine != 's390x' and sys_platform == 'linux'
+    # via keyring
+sniffio==1.3.1
+    # via anthropic
+trove-classifiers==2026.1.14.14
+    # via hatchling
+twine==6.2.0
+typing-extensions==4.15.0
+    # via
+    #   anthropic
+    #   anyio
+    #   pydantic
+    #   pydantic-core
+    #   typing-inspection
+typing-inspection==0.4.2
+    # via pydantic
+urllib3==2.6.3
+    # via
+    #   id
+    #   requests
+    #   twine