papers-cli 2.6__tar.gz → 2.7__tar.gz

papers_cli-2.7/.github/workflows/pypi.yml

@@ -0,0 +1,36 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - '*'
+
+jobs:
+  build-and-publish:
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+    permissions:
+      id-token: write  # This is required for OIDC
+      contents: read
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v2
+
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.x'
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install setuptools wheel twine
+
+    - name: Build distribution
+      run: |
+        python setup.py sdist bdist_wheel
+
+    - name: Publish to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1

{papers_cli-2.6 → papers_cli-2.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: papers-cli
-Version: 2.6
+Version: 2.7
 Summary: utilities to keep your PDF library organized
 Author-email: Mahé Perrette <mahe.perrette@gmail.com>
 License: MIT

{papers_cli-2.6 → papers_cli-2.7}/papers/__main__.py

@@ -9,12 +9,14 @@ import subprocess as sp
 import shutil
 import itertools
 import fnmatch   # unix-like match
+import hashlib
+import time
 
 import papers
 from papers import logger
 from papers.extract import extract_pdf_doi, isvaliddoi, extract_pdf_metadata
 from papers.extract import fetch_bibtex_by_doi
-from papers.encoding import parse_file, format_file, family_names, format_entries
+from papers.encoding import parse_file, format_file, family_names, format_entries, standard_name
 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.bib import Biblio, FUZZY_RATIO, DEFAULT_SIMILARITY, entry_filecheck, backupfile as backupfile_func, isvalidkey
@@ -223,6 +225,12 @@ def savebib(biblio, config):
         # config.gitcommit()
 
 
+def view_entry_files(biblio, entry):
+    for f in biblio.get_files(entry):
+        logger.info(f"opening {f} ...")
+        view_pdf(f)
+
+
 def set_keyformat_config_from_cmd(o, config):
     """
     Given options and a config state, applies the desired key options to the config.
@@ -505,6 +513,8 @@ def addcmd(parser, o, config):
     kw = {'on_conflict':o.mode, 'check_duplicate':not o.no_check_duplicate,
             'mergefiles':not o.no_merge_files, 'update_key':o.update_key}
 
+    entries = []
+
     if len(o.file) > 1:
         if o.attachment:
             logger.error('--attachment is only valid for one PDF / BIBTEX entry')
@@ -514,35 +524,37 @@ def addcmd(parser, o, config):
             raise PapersExit()
 
     if len(o.file) == 0:
-        if not o.doi:
-            logger.error('Please provide either a PDF file or BIBTEX entry or specify `--doi DOI`')
+        if o.edit:
+            pass
+        elif not o.doi:
+            logger.error('Please provide either a PDF file or BIBTEX entry or specify `--doi DOI` or `--edit`')
             raise PapersExit()
         elif o.no_query_doi:
             logger.error('If no file is present, --no-query-doi is not compatible with --doi')
             raise PapersExit()
         else:
-            biblio.fetch_doi(o.doi, attachments=o.attachment, rename=o.rename, copy=o.copy, **kw)
+            entries.extend( biblio.fetch_doi(o.doi, attachments=o.attachment, rename=o.rename, copy=o.copy, **kw) )
 
     for file in o.file:
         try:
             if os.path.isdir(file):
                 if o.recursive:
-                    biblio.scan_dir(file, rename=o.rename, copy=o.copy,
+                    entries.extend( biblio.scan_dir(file, rename=o.rename, copy=o.copy,
                                 search_doi=not o.no_query_doi,
                                 search_fulltext=not o.no_query_fulltext,
-                                **kw)
+                                **kw) )
                 else:
                     raise ValueError(file+' is a directory, requires --recursive to explore')
 
             elif file.endswith('.pdf'):
-                biblio.add_pdf(file, attachments=o.attachment, rename=o.rename, copy=o.copy,
+                entries.extend( biblio.add_pdf(file, attachments=o.attachment, rename=o.rename, copy=o.copy,
                            search_doi=not o.no_query_doi,
                            search_fulltext=not o.no_query_fulltext,
                            scholar=o.scholar, doi=o.doi,
-                           **kw)
+                           **kw) )
 
             else: # file.endswith('.bib'):
-                biblio.add_bibtex_file(file, attachments=o.attachment, rename=o.rename, copy=o.copy, **kw)
+                entries.extend( biblio.add_bibtex_file(file, attachments=o.attachment, rename=o.rename, copy=o.copy, **kw) )
 
         except Exception as error:
             # print(error)
@@ -554,8 +566,43 @@ def addcmd(parser, o, config):
                     logger.error('use --ignore to add other files anyway')
                 raise PapersExit()
 
+    # The list of new entries potentially contains duplicates if more than one file is added sequentially
+    # If action is required on the added entry, we need to make sure we're consistent with the biblio.
+    if len(entries) > 1 and (o.edit or o.open):
+        unique_keys = set(biblio.key(e) for e in entries)
+        entries = [e for e in biblio.entries if biblio.key(e) in unique_keys]
+
+    if o.edit:
+        if len(entries) == 0:
+            entries = [{
+                "ID": "EDIT-NEW-KEY",
+                "ENTRYTYPE": "article",
+                "author": standard_name("John Doe and Jane Roe"),
+                "title": "",
+                "journal": "",
+                "year": "",
+                "doi": o.doi or "",
+                "file": format_file(o.attachment or [], relative_to=biblio.relative_to),
+                }]
+
+        try:
+            otherentries = [e for e in biblio.entries if e not in entries]
+            entries = edit_entries(entries)
+            entries = [{k:v for k,v in e.items() if v != ""} for e in entries]
+            biblio.db.entries = otherentries
+            for e in entries:
+                biblio.insert_entry(e, **kw)
+
+        except Exception as error:
+            logger.error(str(error))
+            return
+
     savebib(biblio, config)
 
+    if o.open:
+        for e in entries:
+            view_entry_files(biblio, e)
+
 def checkcmd(parser, o, config):
     """
     Loops over the entire bib file that the Papers install sees, and checks each entry for formatting and for the existance of duplicates.  Then writes the Biblio object back to your Bibtex file.
@@ -801,9 +848,7 @@ def listcmd(parser, o, config):
 
     elif o.open:
         for e in entries:
-            for f in biblio.get_files(e):
-                logger.info(f"opening {f} ...")
-                view_pdf(f)
+            view_entry_files(biblio, e)
 
     elif o.field:
         # entries = [{k:e[k] for k in e if k in o.field+['ID','ENTRYTYPE']} for e in entries]
@@ -985,6 +1030,10 @@ def get_parser(config=None):
     grp.add_argument('-c','--copy', action='store_true',
         help='copy file instead of moving them')
 
+    grp = addp.add_argument_group('actions')
+    grp.add_argument('-e', '--edit', action='store_true', help='edit entry')
+    grp.add_argument('-o', '--open', action='store_true', help='open files')
+
     # check
     # =====
     checkp = subparsers.add_parser('check', description='check and fix entries',

{papers_cli-2.6 → papers_cli-2.7}/papers/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '2.6'
-__version_tuple__ = version_tuple = (2, 6)
+__version__ = version = '2.7'
+__version_tuple__ = version_tuple = (2, 7)

{papers_cli-2.6 → papers_cli-2.7}/papers/bib.py

@@ -285,8 +285,8 @@ class Biblio:
         # additional checks on DOI etc...
         if check_duplicate:
             logger.debug('check duplicates : TRUE')
-            self.insert_entry_check(entry, update_key=update_key, rename=rename, copy=copy, **checkopt)
-            return
+            print("entering...")
+            return self.insert_entry_check(entry, update_key=update_key, rename=rename, copy=copy, **checkopt)
         else:
             logger.debug('check duplicates : FALSE')
 
@@ -312,13 +312,14 @@ class Biblio:
 
         if rename: self.rename_entry_files(entry, copy=copy)
 
-    def insert_entry_check(self, entry, update_key=False, mergefiles=True, on_conflict='i', rename=False, copy=False):
+        return [ entry ]
 
+    def insert_entry_check(self, entry, update_key=False, mergefiles=True, on_conflict='i', rename=False, copy=False):
         duplicates = [e for e in self.entries if self.eq(e, entry)]
 
         if not duplicates:
             logger.debug('not a duplicate')
-            self.insert_entry(entry, update_key, rename=rename, copy=copy)
+            return self.insert_entry(entry, update_key, rename=rename, copy=copy)
 
 
         else:
@@ -336,7 +337,7 @@ class Biblio:
                 logger.debug('exact duplicate')
                 if rename: self.rename_entry_files(candidate, copy=copy)
                 print("Existing entry:", self.key(entry))
-                return  # do nothing
+                return [ entry ] # do nothing
 
             if update_key and entry['ID'] != candidate['ID']:
                 logger.info('duplicate :: update key to match existing entry: {} => {}'.format(entry['ID'], candidate['ID']))
@@ -355,13 +356,15 @@ class Biblio:
                 entry = candidate
                 if rename: self.rename_entry_files(candidate, copy=copy)
                 print("Existing entry:", self.key(entry))
-                return  # do nothing
+                return [ entry ] # do nothing
 
             logger.debug('conflict resolution: '+on_conflict)
             resolved = conflict_resolution_on_insert(candidate, entry, mode=on_conflict)
             self.entries.remove(candidate) # maybe in resolved entries
+            entries = []
             for e in resolved:
-                self.insert_entry(e, update_key, rename=rename, copy=copy)
+                entries.extend( self.insert_entry(e, update_key, rename=rename, copy=copy) )
+            return entries
 
 
     def generate_key(self, entry):
@@ -389,6 +392,7 @@ class Biblio:
         bib = bibtexparser.loads(bibtex)
         if convert_to_unicode:
             bib = bibtexparser.customization.convert_to_unicode(bib)
+        entries = []
         for e in bib.entries:
             files = []
             if "file" in e:
@@ -399,7 +403,8 @@ class Biblio:
             if files:
                 self.set_files(e, files)
 
-            self.insert_entry(e, **kw)
+            entries.extend( self.insert_entry(e, **kw) )
+        return entries
 
 
     def add_bibtex_file(self, file, **kw):
@@ -409,8 +414,7 @@ class Biblio:
 
     def fetch_doi(self, doi, **kw):
         bibtex = fetch_bibtex_by_doi(doi)
-        self.add_bibtex(bibtex, **kw)
-
+        return self.add_bibtex(bibtex, **kw)
 
     def add_pdf(self, pdf, attachments=None, search_doi=True, search_fulltext=True, scholar=False, doi=None, **kw):
 
@@ -435,10 +439,10 @@ class Biblio:
 
         kw.pop('update_key', True)
             # logger.warning('fetched key is always updated when adding PDF to existing bib')
-        self.insert_entry(entry, update_key=True, **kw)
+        return self.insert_entry(entry, update_key=True, **kw)
 
 
-    def scan_dir(self, direc, search_doi=True, search_fulltext=True, **kw):
+    def scan_dir_iter(self, direc, search_doi=True, search_fulltext=True, **kw):
 
         for root, direcs, files in os.walk(direc):
             dirname = os.path.basename(root)
@@ -450,7 +454,7 @@ class Biblio:
                 logger.debug('read from hidden bibtex')
                 try:
                     entry = read_entry_dir(root, relative_to=self.relative_to)
-                    self.insert_entry(entry, **kw)
+                    yield from self.insert_entry(entry, **kw)
                 except Exception:
                     logger.warning(root+'::'+str(error))
                 continue
@@ -461,13 +465,17 @@ class Biblio:
                 path = os.path.join(root, file)
                 try:
                     if file.endswith('.pdf'):
-                        self.add_pdf(path, search_doi=search_doi, search_fulltext=search_fulltext, **kw)
+                        yield from self.add_pdf(path, search_doi=search_doi, search_fulltext=search_fulltext, **kw)
                     elif file.endswith('.bib'):
-                        self.add_bibtex_file(path, **kw)
+                        yield from self.add_bibtex_file(path, **kw)
                 except Exception as error:
                     logger.warning(path+'::'+str(error))
                     continue
 
+    def scan_dir(self, direc, **kw):
+        " like scan_dir_iter but returns a list"
+        return list(self.scan_dir_iter(direc, **kw))
+
 
     def format(self):
         return bibtexparser.dumps(self.db)

{papers_cli-2.6 → papers_cli-2.7}/papers/duplicate.py

@@ -46,7 +46,7 @@ def groupby_equal(entries, eq=None):
         else:
             group = groups[k]
         group.append(e)
-    return sorted(groups.items()) 
+    return sorted(groups.items())
 
 
 def search_duplicates(entries, key=None, eq=None, issorted=False, filter_key=None):

{papers_cli-2.6 → papers_cli-2.7}/papers_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: papers-cli
-Version: 2.6
+Version: 2.7
 Summary: utilities to keep your PDF library organized
 Author-email: Mahé Perrette <mahe.perrette@gmail.com>
 License: MIT

{papers_cli-2.6 → papers_cli-2.7}/papers_cli.egg-info/SOURCES.txt

@@ -5,6 +5,7 @@ README.md
 pyproject.toml
 requirements.txt
 setup.py
+.github/workflows/pypi.yml
 .github/workflows/tests.yml
 papers/__init__.py
 papers/__main__.py