papers-cli 2.15.5__tar.gz → 2.16.2__tar.gz

{papers_cli-2.15.5 → papers_cli-2.16.2}/.github/workflows/pypi.yml

@@ -1,9 +1,13 @@
+# Publishes to PyPI on tag push (e.g. v2.16.1).
+# If this job fails with "400 Bad Request", the package may still be on PyPI: that usually
+# means the workflow ran twice (e.g. tag pushed twice or job re-run) and the second upload
+# failed because the version already exists. Use verbose: true output to see the real error.
 name: Publish to PyPI
 
 on:
   push:
     tags:
-      - '*'
+      - 'v*'
 
 jobs:
   build-and-publish:
@@ -16,10 +20,10 @@ jobs:
 
     steps:
     - name: Checkout code
-      uses: actions/checkout@v2
+      uses: actions/checkout@v5
 
     - name: Set up Python
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v5
       with:
         python-version: '3.x'
 
@@ -33,4 +37,7 @@ jobs:
         python setup.py sdist bdist_wheel
 
     - name: Publish to PyPI
-      uses: pypa/gh-action-pypi-publish@release/v1
+      uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        # Show full PyPI error (e.g. "400 File already exists") when upload fails
+        verbose: true

papers_cli-2.16.2/.github/workflows/release.yml

@@ -0,0 +1,58 @@
+name: Create GitHub Release
+
+on:
+  push:
+    tags:
+      - 'v*'
+
+jobs:
+  create-release:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write  # Required to create releases
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+      with:
+        fetch-depth: 0  # Fetch all history for changelog generation
+
+    - name: Get tag name
+      id: tag
+      run: echo "tag=${GITHUB_REF#refs/tags/}" >> $GITHUB_OUTPUT
+
+    - name: Generate changelog
+      id: changelog
+      run: |
+        # Get the previous tag
+        PREV_TAG=$(git describe --tags --abbrev=0 HEAD^ 2>/dev/null || echo "")
+
+        if [ -z "$PREV_TAG" ]; then
+          # First release - get all commits
+          CHANGES=$(git log --pretty=format:"- %s (%h)" --no-merges)
+        else
+          # Get commits since previous tag
+          CHANGES=$(git log ${PREV_TAG}..HEAD --pretty=format:"- %s (%h)" --no-merges)
+        fi
+
+        # Save to file to handle multiline content
+        echo "$CHANGES" > changelog.txt
+
+        # Also output to GitHub output
+        echo "changelog<<EOF" >> $GITHUB_OUTPUT
+        echo "$CHANGES" >> $GITHUB_OUTPUT
+        echo "EOF" >> $GITHUB_OUTPUT
+
+    - name: Create Release
+      uses: actions/create-release@v1
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      with:
+        tag_name: ${{ steps.tag.outputs.tag }}
+        release_name: Release ${{ steps.tag.outputs.tag }}
+        body: |
+          ## Changes in ${{ steps.tag.outputs.tag }}
+
+          ${{ steps.changelog.outputs.changelog }}
+        draft: false
+        prerelease: false

{papers_cli-2.15.5 → papers_cli-2.16.2}/.github/workflows/tests.yml

@@ -10,12 +10,12 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [ "3.9", "3.10", "3.11", "3.12", "3.13"  ]
+        python-version: [ "3.9", "3.10", "3.11", "3.12", "3.13", "3.14", "3.14t"  ]
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v5
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies

{papers_cli-2.15.5 → papers_cli-2.16.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: papers-cli
-Version: 2.15.5
+Version: 2.16.2
 Summary: utilities to keep your PDF library organized
 Author-email: Mahé Perrette <mahe.perrette@gmail.com>
 License: MIT
@@ -13,7 +13,7 @@ License-File: LICENSE
 Requires-Dist: PyMuPDF
 Requires-Dist: unidecode
 Requires-Dist: crossrefapi
-Requires-Dist: bibtexparser
+Requires-Dist: bibtexparser>=2.0.0b2
 Requires-Dist: scholarly
 Requires-Dist: rapidfuzz
 Requires-Dist: python-slugify
@@ -21,7 +21,8 @@ Requires-Dist: bs4
 Dynamic: license-file
 
 [![pypi](https://img.shields.io/pypi/v/papers-cli)](https://pypi.org/project/papers-cli)
-[![python](https://img.shields.io/badge/python-3.13-blue.svg)]()
+[![python](https://img.shields.io/badge/python-3.9-blue.svg)]()
+[![python](https://img.shields.io/badge/python-3.14t-blue.svg)]()
 [![test](https://github.com/perrette/papers/workflows/CI/badge.svg?query=branch%3Amaster)](https://github.com/perrette/papers/actions)
 
 # papers
@@ -100,6 +101,12 @@ That is equivalent to doing:
 
 See [Control fields when renaming file](#control-fields-when-renaming-file) for how to specify file naming patterns.
 
+It is also possible to do this on a full directory of files, recursively:
+
+   papers add --rename --recursive /home/perette/playground/papers/papers_test
+
+where, above, the `papers_test` directory contains a few PDF files.  For each PDF, `papers` will attempt to extract the metadata and add the relevant file to the bibliography and renamed files to the files directory.
+
 ### Add library entry from its DOI
 
 If you already know the DOI of a PDF, and don't want to gamble the fulltext search and match, you can indicate it via `--doi`:

{papers_cli-2.15.5 → papers_cli-2.16.2}/README.md

@@ -1,5 +1,6 @@
 [![pypi](https://img.shields.io/pypi/v/papers-cli)](https://pypi.org/project/papers-cli)
-[![python](https://img.shields.io/badge/python-3.13-blue.svg)]()
+[![python](https://img.shields.io/badge/python-3.9-blue.svg)]()
+[![python](https://img.shields.io/badge/python-3.14t-blue.svg)]()
 [![test](https://github.com/perrette/papers/workflows/CI/badge.svg?query=branch%3Amaster)](https://github.com/perrette/papers/actions)
 
 # papers
@@ -78,6 +79,12 @@ That is equivalent to doing:
 
 See [Control fields when renaming file](#control-fields-when-renaming-file) for how to specify file naming patterns.
 
+It is also possible to do this on a full directory of files, recursively:
+
+   papers add --rename --recursive /home/perette/playground/papers/papers_test
+
+where, above, the `papers_test` directory contains a few PDF files.  For each PDF, `papers` will attempt to extract the metadata and add the relevant file to the bibliography and renamed files to the files directory.
+
 ### Add library entry from its DOI
 
 If you already know the DOI of a PDF, and don't want to gamble the fulltext search and match, you can indicate it via `--doi`:

{papers_cli-2.15.5 → papers_cli-2.16.2}/papers/__main__.py

@@ -18,9 +18,11 @@ from papers.extract import extract_pdf_doi, isvaliddoi, extract_pdf_metadata
 from papers.extract import fetch_bibtex_by_doi, fetch_bibtex_by_fulltext_crossref, fetch_bibtex_by_fulltext_scholar
 from papers.encoding import parse_file, format_file, family_names, format_entries, standard_name, format_entry, parse_keywords, format_key
 from papers.config import bcolors, Config, search_config, CONFIG_FILE, CONFIG_FILE_LOCAL, DATA_DIR, CONFIG_FILE_LEGACY, BACKUP_DIR
-from papers.duplicate import list_duplicates, list_uniques, edit_entries
+from papers.duplicate import list_duplicates, list_uniques, edit_entries, title_id
+from papers.entries import get_entry_val
 from papers.bib import (Biblio, FUZZY_RATIO, DEFAULT_SIMILARITY, entry_filecheck,
-                        backupfile as backupfile_func, isvalidkey, DuplicateKeyError, clean_filesdir)
+                        backupfile as backupfile_func, isvalidkey, DuplicateKeyError, clean_filesdir,
+                        are_duplicates)
 from papers.utils import move, checksum, view_pdf, open_folder
 from papers import __version__
 
@@ -149,10 +151,10 @@ def _restore_from_backupdir_wrapped(config, restore_files=False):
     assert len(biblio.entries) == len(biblio_clean.entries)
 
     for e, e_clean in zip(biblio.entries, biblio_clean.entries):
-        assert e['ID'] == e_clean['ID'], f"{e['ID']} != {e_clean['ID']})"
+        assert get_entry_val(e, 'ID', '') == get_entry_val(e_clean, 'ID', ''), f"{get_entry_val(e, 'ID', '')} != {get_entry_val(e_clean, 'ID', '')})"
         files = biblio.get_files(e)
         files_clean = biblio_clean.get_files(e_clean)
-        assert len(files) == len(files_clean), f"{e['ID']} :: files {len(files)} != {len(files_clean)})"
+        assert len(files) == len(files_clean), f"{get_entry_val(e, 'ID', '')} :: files {len(files)} != {len(files_clean)})"
 
         new_files = []
 
@@ -162,7 +164,7 @@ def _restore_from_backupdir_wrapped(config, restore_files=False):
                 logger.debug(f"BACKUP FILE DOES NOT EXISTS: {f_clean} ")
                 logger.debug(f"BACKUP ENTRY: {e_clean['file']} ")
                 logger.debug(f"BROKEN ENTRY: {e['file']} ")
-                logger.warning(f"{e['ID']} :: file link broken => {f} ")
+                logger.warning(f"{get_entry_val(e, 'ID', '')} :: file link broken => {f} ")
                 new_files.append(f)
                 continue
 
@@ -176,7 +178,7 @@ def _restore_from_backupdir_wrapped(config, restore_files=False):
                     new_files.append(f)
 
                 else:
-                    logger.warning(f"{e['ID']} :: file found but does not match backup (keep pointer to backup): {f} != {f_clean}")
+                    logger.warning(f"{get_entry_val(e, 'ID', '')} :: file found but does not match backup (keep pointer to backup): {f} != {f_clean}")
                     new_files.append(f_clean)
 
             # original bibtex link is broken, --restore-file is active
@@ -187,7 +189,7 @@ def _restore_from_backupdir_wrapped(config, restore_files=False):
 
                 except Exception as error:
                     logger.error(f"{error}")
-                    logger.error(f"{e['ID']} :: failed to restore file (keep pointer to backup)")
+                    logger.error(f"{get_entry_val(e, 'ID', '')} :: failed to restore file (keep pointer to backup)")
                     new_files.append(f_clean)
                     pass
 
@@ -661,11 +663,11 @@ def addcmd(parser, o, config):
     # compare entries to inform user
     # this is not very efficient but I have yet to hear a complaint about speed
 
-    old_set = set(e["ID"] for e in biblio_init.entries)
-    old_entries_by_key = {e["ID"]:e for e in biblio_init.db.entries}
-    new_set = set(e["ID"] for e in biblio.entries)
-    new_entries_by_key = {e["ID"]:e for e in biblio.db.entries}
-    modified_set = set(e["ID"] for e in entries ).intersection(set.intersection(old_set, new_set))
+    old_set = set(get_entry_val(e, 'ID', '') for e in biblio_init.entries)
+    old_entries_by_key = {get_entry_val(e, 'ID', ''): e for e in biblio_init.db.entries}
+    new_set = set(get_entry_val(e, 'ID', '') for e in biblio.entries)
+    new_entries_by_key = {get_entry_val(e, 'ID', ''): e for e in biblio.db.entries}
+    modified_set = set(get_entry_val(e, 'ID', '') for e in entries).intersection(set.intersection(old_set, new_set))
 
     for ID in sorted(old_set - new_set):
         print(format_entry(biblio_init, old_entries_by_key[ID], prefix="Removed"))
@@ -699,7 +701,7 @@ def checkcmd(parser, o, config):
     #     o.fix_key = True
 
     for e in biblio.entries:
-        if o.keys and e.get('ID','') not in o.keys:
+        if o.keys and get_entry_val(e, 'ID', '') not in o.keys:
             continue
         biblio.fix_entry(e, fix_doi=o.fix_doi, fetch=o.fetch, fetch_all=o.fetch_all, fix_key=o.fix_key,
                      auto_key=o.auto_key, format_name=o.format_name, encoding=o.encoding,
@@ -816,11 +818,11 @@ def listcmd(parser, o, config):
         return _match(word, target, fuzzy=o.fuzzy, substring=not o.strict)
 
     def _nfiles(e):
-        return len(parse_file(e.get('file',''), relative_to=biblio.relative_to))
+        return len(parse_file(get_entry_val(e, 'file', ''), relative_to=biblio.relative_to))
 
 
     def _requiresreview(e):
-        if not isvalidkey(e.get('ID','')): return True
+        if not isvalidkey(get_entry_val(e, 'ID', '')): return True
         if 'doi' in e and not isvaliddoi(e['doi']): return True
         if 'author' not in e: return True
         if 'title' not in e: return True
@@ -844,17 +846,17 @@ def listcmd(parser, o, config):
                 if 'doi' in e and not isvaliddoi(e['doi']):
                     e['doi'] = bcolors.FAIL + e['doi'] + bcolors.ENDC
     if o.has_file:
-        entries = [e for e in entries if e.get('file','')]
+        entries = [e for e in entries if get_entry_val(e, 'file', '')]
     if o.no_file:
-        entries = [e for e in entries if not e.get('file','')]
+        entries = [e for e in entries if not get_entry_val(e, 'file', '')]
     if o.broken_file:
-        entries = [e for e in entries if e.get('file','') and any([not os.path.exists(f) for f in parse_file(e['file'], relative_to=biblio.relative_to)])]
+        entries = [e for e in entries if get_entry_val(e, 'file', '') and any([not os.path.exists(f) for f in parse_file(e['file'], relative_to=biblio.relative_to)])]
 
 
     if o.doi:
         entries = [e for e in entries if 'doi' in e and _longmatch(e['doi'], o.doi)]
     if o.key:
-        entries = [e for e in entries if 'ID' in e and _longmatch(e['ID'], o.key)]
+        entries = [e for e in entries if _longmatch(get_entry_val(e, 'ID', ''), o.key)]
     if o.year:
         entries = [e for e in entries if 'year' in e and _longmatch(e['year'], o.year)]
     if o.first_author:
@@ -881,7 +883,7 @@ def listcmd(parser, o, config):
     if o.duplicates_key:
         entries = list_dup(entries, key=biblio.key, issorted=True)
     if o.duplicates_doi:
-        entries = list_dup(entries, key=lambda e:e.get('doi',''), filter_key=isvaliddoi)
+        entries = list_dup(entries, key=lambda e: get_entry_val(e, 'doi', ''), filter_key=isvaliddoi)
     if o.duplicates_tit:
         entries = list_dup(entries, key=title_id)
     if o.duplicates:
@@ -889,7 +891,7 @@ def listcmd(parser, o, config):
         # I think that's because we might need to be inclusive here, whereas the default is conservative (parameter used for several functions with possibly differing requirements).
         # (otherwise we'd have used the command-line option o.similarity, or possibly DEFAULT_SIMILARITY)
         # Might need to revise later (the question mark is from a review after a long time without use)
-        eq = lambda a, b: a['ID'] == b['ID'] or are_duplicates(a, b, similarity="PARTIAL", fuzzy_ratio=o.fuzzy_ratio)
+        eq = lambda a, b: get_entry_val(a, 'ID', '') == get_entry_val(b, 'ID', '') or are_duplicates(a, b, similarity="PARTIAL", fuzzy_ratio=o.fuzzy_ratio)
         entries = list_dup(entries, eq=eq)
 
     if o.add_keywords:
@@ -919,7 +921,7 @@ def listcmd(parser, o, config):
         otherentries = [e for e in biblio.db.entries if e not in entries]
         try:
             entries = edit_entries(entries)
-            biblio.db.entries = otherentries + entries
+            biblio.entries = otherentries + entries
         except Exception as error:
             logger.error(str(error))
             return
@@ -933,7 +935,7 @@ def listcmd(parser, o, config):
 
     elif o.delete:
         for e in entries:
-            biblio.db.entries.remove(e)
+            biblio.db.remove(e)
         savebib(biblio, config)
 
     elif o.open:
@@ -943,10 +945,10 @@ def listcmd(parser, o, config):
     elif o.field:
         # entries = [{k:e[k] for k in e if k in o.field+['ID','ENTRYTYPE']} for e in entries]
         for e in entries:
-            print(format_key(e, no_key=o.no_key),*[e.get(k, "") for k in o.field])
+            print(format_key(e, no_key=o.no_key),*[get_entry_val(e, k, "") for k in o.field])
     elif o.key_only:
         for e in entries:
-            print(e['ID'])
+            print(get_entry_val(e, 'ID', ''))
     elif o.one_liner:
         for e in entries:
             print(format_entry(biblio, e, no_key=o.no_key))

{papers_cli-2.15.5 → papers_cli-2.16.2}/papers/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '2.15.5'
-__version_tuple__ = version_tuple = (2, 15, 5)
+__version__ = version = '2.16.2'
+__version_tuple__ = version_tuple = (2, 16, 2)
 
-__commit_id__ = commit_id = 'gbad573f0d'
+__commit_id__ = commit_id = 'g60ea4dbb9'