Import is working

* Various bugfixes
* Bugfix with utf-8

README.md

@@ -110,6 +110,7 @@ Here are some sources of inspirations for this project :
 
 A list of ideas and TODO. Don't hesitate to give feedback on the ones you really want or to propose your owns.
 
+50. Anti-duplicate ?
 65. Look for published version in arXiv
 70. No DOI for HAL => metadata with SOAP API… don't want to handle it for now :/
 80. Search engine
@@ -118,10 +119,10 @@ A list of ideas and TODO. Don't hesitate to give feedback on the ones you really
 
 ## Issues ?
 
-* Remove the watermarks on pdf files => done, some warning in okular on generated pdf, but seems ok. Seems to be a bug in Okular.
+* Multiplication of {{}}
-
 
 ## Thanks
 
 * Nathan Grigg for his [arxiv2bib](https://pypi.python.org/pypi/arxiv2bib/1.0.5#downloads) python module
 * François Boulogne for his [python-bibtexparser](https://github.com/sciunto/python-bibtexparser) python module and his integration of new requested features
+* pyparsing [search parser example](http://pyparsing.wikispaces.com/file/view/searchparser.py)

backend.py

@@ -47,7 +47,7 @@ def getNewName(src, bibtex, tag=''):
                 tools.warning("Unable to create tag dir " +
                               params.folder+tag+".")
 
-        new_name = (params.folder + tools.slugify(tag) +
+        new_name = (params.folder + tools.slugify(tag) + '/' +
                     tools.slugify(new_name) + tools.getExtension(src))
 
     return new_name
@@ -256,6 +256,11 @@ def getEntries():
 
 
 def updateArXiv(entry):
+    """Look for new versions of arXiv entry `entry`
+
+    Returns False if no new versions or not an arXiv entry,
+    Updates the file and returns the new bibtex otherwise.
+    """
     bibtex = getBibtex(entry)
     # Check arXiv
     if('ArchivePrefix' not in bibtex and
@@ -280,3 +285,11 @@ def updateArXiv(entry):
         return last_bibtex
     else:
         return False
+
+
+def search(query):
+    """Performs a search in the bibtex index.
+
+    Param: query is a dict of keys and the query for these keys
+    """
+    raise Exception('TODO')

main.py

@@ -21,7 +21,8 @@ EDITOR = os.environ.get('EDITOR') if os.environ.get('EDITOR') else 'vim'
 def checkBibtex(filename, bibtex):
     print("The bibtex entry found for "+filename+" is:")
 
-    bibtex = BibTexParser(bibtex, customization=homogeneize_latex_encoding)
+    bibtex = BibTexParser(bibtex.encode('utf-8'),
+                          customization=homogeneize_latex_encoding)
     bibtex = bibtex.get_entry_dict()
     if len(bibtex) > 0:
         bibtex_name = bibtex.keys()[0]
@@ -31,18 +32,22 @@ def checkBibtex(filename, bibtex):
         bibtex_string = ''
     print(bibtex_string)
     check = tools.rawInput("Is it correct? [Y/n] ")
-    old_filename = bibtex['file']
+    try:
+        old_filename = bibtex['file']
+    except:
+        old_filename = False
 
     while check.lower() == 'n':
         with tempfile.NamedTemporaryFile(suffix=".tmp") as tmpfile:
-            tmpfile.write(bibtex_string)
+            tmpfile.write(bibtex_string.encode('utf-8'))
             tmpfile.flush()
             subprocess.call([EDITOR, tmpfile.name])
-            bibtex = BibTexParser(tmpfile.read()+"\n",
+            tmpfile.seek(0)
+            bibtex = BibTexParser(tmpfile.read().encode('utf-8')+"\n",
                                   customization=homogeneize_latex_encoding)
 
         bibtex = bibtex.get_entry_dict()
-        if 'file' not in bibtex:
+        if old_filename is not False and 'file' not in bibtex:
             tools.warning("Invalid bibtex entry. No filename given.")
             tools.rawInput("Press Enter to go back to editor.")
             check = 'n'
@@ -56,7 +61,7 @@ def checkBibtex(filename, bibtex):
             print("\nThe bibtex entry for "+filename+" is:")
             print(bibtex_string)
             check = tools.rawInput("Is it correct? [Y/n] ")
-    if old_filename != bibtex['file']:
+    if old_filename is not False and old_filename != bibtex['file']:
         try:
             shutil.move(old_filename, bibtex['file'])
         except:
@@ -206,7 +211,7 @@ def editEntry(entry, file_id='both'):
 
     try:
         with open(params.folder+'index.bib', 'r') as fh:
-            index = BibTexParser(fh.read(),
+            index = BibTexParser(fh.read().encode('utf-8'),
                                  customization=homogeneize_latex_encoding)
         index = index.get_entry_dict()
     except:
@@ -225,7 +230,7 @@ def downloadFile(url, filetype, manual):
         tmp = tempfile.NamedTemporaryFile(suffix='.'+contenttype)
 
         with open(tmp.name, 'w+') as fh:
-            fh.write(dl)
+            fh.write(dl.encode('utf-8'))
         new_name = addFile(tmp.name, filetype, manual)
         tmp.close()
         return new_name
@@ -237,7 +242,7 @@ def downloadFile(url, filetype, manual):
 def openFile(ident):
     try:
         with open(params.folder+'index.bib', 'r') as fh:
-            bibtex = BibTexParser(fh.read(),
+            bibtex = BibTexParser(fh.read().encode('utf-8'),
                                   customization=homogeneize_latex_encoding)
         bibtex = bibtex.get_entry_dict()
     except:
@@ -410,6 +415,12 @@ if __name__ == '__main__':
                                help="a filename or an identifier")
     parser_update.set_defaults(func='update')
 
+    parser_search = subparsers.add_parser('search', help="search help")
+    # TODO: Check
+    parser_delete.add_argument('query', metavar='entry', nargs='+',
+                               help="your query, see README for more info.")
+    parser_search.set_defaults(func='search')
+
     args = parser.parse_args()
     try:
         if args.func == 'download':

tools.py

@@ -39,12 +39,13 @@ def replaceAll(text, dic):
 def rawInput(string):
     """Flush stdin and then prompt the user for something"""
     tcflush(sys.stdin, TCIOFLUSH)
-    return raw_input(string)
+    return raw_input(string).decode('utf-8')
 
 
 def warning(*objs):
     """Write warnings to stderr"""
-    print("WARNING: ", *objs, file=sys.stderr)
+    printed = [i.encode('utf-8') for i in objs]
+    print("WARNING: ", *printed, file=sys.stderr)
 
 
 def listDir(path):