PEP8

Signed-off-by: Jerome Flesch <[email protected]>

paperwork-backend/paperwork_backend/common/doc.py

@@ -159,7 +159,7 @@ def __get_labels(self):
         labels = []
         try:
             with self.fs.open(self.fs.join(self.path, self.LABEL_FILE),
-                                'r') as file_desc:
+                              'r') as file_desc:
                 for line in file_desc.readlines():
                     line = line.strip()
                     (label_name, label_color) = line.split(",", 1)

paperwork-backend/paperwork_backend/docimport.py

@@ -391,7 +391,9 @@ def get_select_mime_types():
         ]
 
     def __str__(self):
-        return _("Import all image files in the folder in the current document")
+        return (
+            _("Import all image files in the folder in the current document")
+        )
 
 
 class ImageImporter(BaseImporter):

paperwork-backend/paperwork_backend/docsearch.py

@@ -346,7 +346,8 @@ def get(self, obj_id):
         return self.index.get(obj_id)
 
     def get_doc_from_docid(self, docid, doc_type_name=None, inst=True):
-        return self.index.get_doc_from_docid(docid, doc_type_name=doc_type_name,
+        return self.index.get_doc_from_docid(docid,
+                                             doc_type_name=doc_type_name,
                                              inst=inst)
 
     def find_documents(self, sentence, limit=None, must_sort=True,

paperwork-backend/paperwork_backend/fs.py

@@ -80,8 +80,8 @@ def readline(self, size=-1):
         raise OSError("readline() not supported on Gio.File objects")
 
     def readlines(self, hint=-1):
-        logger.warning("readlines() shouldn't be called on a binary file descriptor. This is not cross-platform")
-        all = self.readall()
+        logger.warning("readlines() shouldn't be called on a binary file"
+                       " descriptor. This is not cross-platform")
         return [(x + b"\n") for x in self.readall().split(b"\n")]
 
     def seek(self, offset, whence=os.SEEK_SET):

paperwork-backend/paperwork_backend/shell.py

@@ -11,11 +11,11 @@
 gi.require_version('PangoCairo', '1.0')
 gi.require_version('Poppler', '0.18')
 
-from . import config
-from . import docimport
-from . import docsearch
-from .labels import Label
-from . import fs
+from . import config  # noqa: E402
+from . import docimport  # noqa: E402
+from . import docsearch  # noqa: E402
+from .labels import Label  # noqa: E402
+from . import fs  # noqa: E402
 
 
 FS = fs.GioFileSystem()
@@ -31,13 +31,13 @@ def is_interactive():
 
 def verbose(txt):
     if is_verbose():
-        print (txt)
+        print(txt)
 
 
 def reply(data):
     if "status" not in data:
         data['status'] = 'ok'
-    print (json.dumps(
+    print(json.dumps(
         data, indent=4,
         separators=(',', ': '),
         sort_keys=True
@@ -60,7 +60,7 @@ def _dump_page(page):
         out = ""
         for word in line.word_boxes:
             out += word.content + " "
-        print (out.strip())
+        print(out.strip())
 
 
 def cmd_add_label(docid, label_name, color=None):
@@ -98,7 +98,8 @@ def cmd_add_label(docid, label_name, color=None):
             break
     if not label and not color:
         raise Exception(
-            "Label {} doesn't exist yet, and no color has been provided".format(
+            "Label {} doesn't exist yet, and no color has been"
+            " provided".format(
                 label_name
             )
         )
@@ -410,7 +411,8 @@ def _get_importer(fileuris, doc):
         return importers[0]
     elif not is_interactive():
         raise Exception(
-            "Many way to import {} and running in batch mode. Can't import.\n{}"
+            "Many way to import {} and running in batch mode."
+            " Can't import.\n{}"
             .format(
                 fileuris,
                 ", ".join([str(importer) for importer in importers])
@@ -698,6 +700,7 @@ def cmd_ocr(*args):
         "ocr": [page.pageid for page in pages]
     })
 
+
 def cmd_remove_label(docid, label_name):
     """
     Arguments: <document_id> <label_name>

paperwork-backend/paperwork_backend/util.py

@@ -25,6 +25,8 @@
 import threading
 import unicodedata
 
+import PIL.Image
+
 try:
     import cairo
     CAIRO_AVAILABLE = True
@@ -36,7 +38,6 @@
     import enchant.tokenize
     import Levenshtein
 
-import PIL.Image
 
 logger = logging.getLogger(__name__)
 FORCED_SPLIT_KEYWORDS_REGEX = re.compile("[\n '()]", re.UNICODE)

paperwork-backend/scripts/obfuscate.py

@@ -181,7 +181,7 @@ def main(src_dir, dst_dir):
         print("Words are replaced by pieces of their hash (SHA512)")
         print("")
         print("Example:")
-        print("  %s ~/papers/20100730_0000_01 ~/tmp/20100730_0000_01.anonymized"
+        print("  %s ~/papers/20100730_0000_01 ~/tmp/20100730_0000_01.anon"
               % sys.argv[0])
         sys.exit(1)
     src = sys.argv[1]

paperwork-backend/scripts/stats.py

@@ -135,20 +135,22 @@ def main():
     print("===")
     print("Maximum number of pages in one document: %d" % max_pages)
     print("Maximum word length: %d" % max_word_len)
-    print("Average word length: %f" % (float(total_word_len) / float(nb_words)))
-    print ("Average number of words per page: %f"
-           % (float(nb_words) / float(nb_pages)))
-    print ("Average number of words per document: %f"
-           % (float(nb_words) / float(nb_docs)))
-    print ("Average number of pages per document: %f"
-           % (float(nb_pages) / float(nb_docs)))
-    print ("Average number of unique words per document: %f"
-           % (float(total_nb_unique_words_per_doc) / float(nb_docs)))
+    print("Average word length: %f" % (
+        float(total_word_len) / float(nb_words)
+    ))
+    print("Average number of words per page: %f"
+          % (float(nb_words) / float(nb_pages)))
+    print("Average number of words per document: %f"
+          % (float(nb_words) / float(nb_docs)))
+    print("Average number of pages per document: %f"
+          % (float(nb_pages) / float(nb_docs)))
+    print("Average number of unique words per document: %f"
+          % (float(total_nb_unique_words_per_doc) / float(nb_docs)))
     for key in label_keys:
         total = total_labels[key]
         value = total_label_accuracy[key]
-        print ("Average accuracy of label prediction (%s): %f%%"
-               % (key, (100 * value / total)))
+        print("Average accuracy of label prediction (%s): %f%%"
+              % (key, (100 * value / total)))
 
 
 if __name__ == "__main__":

paperwork-gtk/nsis/gen_installer_nsi.py

@@ -1,13 +1,19 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
+# TODO(Jflesch): PEP8 ...
+# flake8: noqa
+
 import re
 import sys
 
 from paperwork_backend.util import find_language
 
 
-DOWNLOAD_URI = "https://download.openpaper.work/${PRODUCT_SHORT_VERSION}/paperwork_${PRODUCT_VERSION}_win64.zip"
+DOWNLOAD_URI = (
+    "https://download.openpaper.work/${PRODUCT_SHORT_VERSION}/"
+    "paperwork_${PRODUCT_VERSION}_win64.zip"
+)
 
 ALL_LANGUAGES = [
     "eng",  # English (always first)
@@ -110,7 +116,7 @@
     "cym",  # Welsh
     "yid",
  ]
- 
+
 UNKNOWN_LANGUAGE = {
     'download_section': """
         Section /o "{long}" SEC_{upper}
@@ -274,7 +280,7 @@
 
   ; CreateShortCut "$DESKTOP.lnk" "$INSTDIR\\paperwork.exe"
   ; CreateShortCut "$STARTMENU.lnk" "$INSTDIR\\paperwork.exe"
-  
+
   SetOutPath "$INSTDIR\\Tesseract"
   CreateDirectory "$INSTDIR\\Tesseract"
   nsisunz::UnzipToLog "$PLUGINSDIR\\tesseract.zip" "$INSTDIR"
@@ -400,7 +406,7 @@ def get_lang_infos(lang_name):
     suffix = "" if len(lang) <= 1 else lang[1]
 
     lang = find_language(lang_name)
-    
+
     if not suffix:
         long_name = lang.name
     else:
@@ -419,7 +425,7 @@ def main(args):
         return
 
     download_uri = DOWNLOAD_URI
-    
+
     if len(args) == 3:
         version = short_version = args[1]
         download_uri = args[2]
@@ -446,12 +452,12 @@ def main(args):
             txt = txt.format(**get_lang_infos(lang_name))
             out_fd.write(txt)
         out_fd.write("""
-SectionGroupEnd        
+SectionGroupEnd
 """)
-                
+
 
         out_fd.write(MIDDLE)
-        
+
         for lang_name in ALL_LANGUAGES:
             print ("Adding strings section {}".format(lang_name))
             lang = UNKNOWN_LANGUAGE
@@ -460,7 +466,7 @@ def main(args):
             txt = lang['lang_strings']
             txt = txt.format(**get_lang_infos(lang_name))
             out_fd.write(txt)
-            
+
         out_fd.write("""
 !insertmacro MUI_FUNCTION_DESCRIPTION_BEGIN
   !insertmacro MUI_DESCRIPTION_TEXT ${SEC_PAPERWORK} $(DESC_SEC_PAPERWORK)
@@ -480,4 +486,4 @@ def main(args):
     print ("out.nsi written")
 
 if __name__ == "__main__":
-    main(sys.argv)
+    main(sys.argv)

paperwork-gtk/pyinstaller/paperwork_launcher.py

@@ -8,4 +8,4 @@
         multiprocessing.freeze_support()
 
     from paperwork.paperwork import main
-    main()
+    main()

paperwork-gtk/scripts/compare_algorithms.py

@@ -14,20 +14,20 @@
 gi.require_version('PangoCairo', '1.0')
 gi.require_version('Gtk', '3.0')
 
-import enchant
-import enchant.tokenize
-import Levenshtein
-import pillowfight
-import pyocr
+import enchant  # noqa: E402
+import enchant.tokenize  # noqa: E402
+import Levenshtein  # noqa: E402
+import pillowfight  # noqa: E402
+import pyocr  # noqa: E402
 
-from paperwork_backend import config
-from paperwork_backend import docsearch
+from paperwork_backend import config  # noqa: E402
+from paperwork_backend import docsearch  # noqa: E402
 
-from paperwork.frontend.util.jobs import Job
-from paperwork.frontend.util.jobs import JobFactory
-from paperwork.frontend.util.jobs import JobScheduler
+from paperwork.frontend.util.jobs import Job  # noqa: E402
+from paperwork.frontend.util.jobs import JobFactory  # noqa: E402
+from paperwork.frontend.util.jobs import JobScheduler  # noqa: E402
 
-from gi.repository import GObject
+from gi.repository import GObject  # noqa: E402
 
 
 """
@@ -191,10 +191,10 @@ def _add_score(self, txt, stats):
             stats['maybe'] += 1
 
     def _print_stats(self):
-        print ("-" * 40)
+        print("-" * 40)
         for algo in ALGORITHMS:
             stats = algo[2]
-            print ("{}".format(algo[0]))
+            print("{}".format(algo[0]))
             sys.stdout.write("  ")
             for (name, value) in stats.items():
                 if not name.startswith("nb_"):
@@ -209,7 +209,7 @@ def _print_stats(self):
                         name, str(value).rjust(5)
                     ))
             sys.stdout.write("\n")
-        print ("-" * 40)
+        print("-" * 40)
 
     def do(self):
         with LOCK:
@@ -231,11 +231,11 @@ def do(self):
             time_per_document = elapsed_time / stats['nb_pages']
             eta = time_per_document * (g_nb_total_pages - stats['nb_pages'])
 
-            print ("")
-            print ("")
-            print ("")
-            print ("")
-            print ("Done: {} ({}/{} = {}% ==> ETA: {})".format(
+            print("")
+            print("")
+            print("")
+            print("")
+            print("Done: {} ({}/{} = {}% ==> ETA: {})".format(
                 self.page_in,
                 stats['nb_pages'], g_nb_total_pages,
                 int(stats['nb_pages'] * 100 / g_nb_total_pages),
@@ -245,6 +245,7 @@ def do(self):
 
             gc.collect()
 
+
 GObject.type_register(JobImageProcessing)
 
 
@@ -298,9 +299,9 @@ def main():
     global g_nb_total_pages
     global g_start_time
 
-    print ("Will use {} for OCR".format(OCR_TOOL.get_name()))
+    print("Will use {} for OCR".format(OCR_TOOL.get_name()))
 
-    print ("Initializing dictionnary ...")
+    print("Initializing dictionnary ...")
     g_lang = "eng"
     if len(sys.argv) > 1:
         g_lang = "fra"
@@ -311,28 +312,28 @@ def main():
     except enchant.tokenize.TokenizerNotFoundError as exc:
         print("Warning: Falling back to default tokenizer ({})".format(exc))
         g_tknzr = enchant.tokenize.get_tokenizer()
-    print ("Done")
+    print("Done")
 
-    print ("Loading documents list ...")
+    print("Loading documents list ...")
     pconfig = config.PaperworkConfig()
     pconfig.read()
     work_dir = pconfig.settings['workdir'].value
     dsearch = docsearch.DocSearch(work_dir)
     dsearch.reload_index()
-    print ("Documents loaded")
-    print ("")
+    print("Documents loaded")
+    print("")
 
-    print ("Initalizing workers ...")
+    print("Initalizing workers ...")
     manager = WorkerManager()
     manager.start()
 
     factory = JobFactoryImageProcessing()
-    print ("Done")
+    print("Done")
 
     g_start_time = datetime.datetime.now()
 
     try:
-        print ("Queueing jobs ...")
+        print("Queueing jobs ...")
         nb_docs = 0
         nb_pages = 0
         for doc in dsearch.docs: