Other random cleanups

Part of Softcatala#50

integration-tests/checkdownloads.py

@@ -79,10 +79,7 @@ def _remove_tmp_directory(self):
         if os.path.exists(self.temp_dir):
             shutil.rmtree(self.temp_dir)
 
-    def check_zipfile(self,
-                      filename,
-                      extensions,
-                      expected_files,
+    def check_zipfile(self, filename, extensions, expected_files,
                       minimum_size):
         tmp_file = tempfile.NamedTemporaryFile()
         link = self._get_link_from_filename(filename)

integration-tests/checksearch.py

@@ -29,8 +29,8 @@ def __init__(self, url):
         self.url = url
 
     def search_source(self, term):
-        url = '{0}/web_search.py?source={1}&project=tots&json=1'
-        url = url.format(self.url, term)
+        url = ('{0}/web_search.py?source={1}&project=tots'
+               '&json=1'.format(self.url, term))
 
         urllib.urlretrieve(url, 'file.txt')
         with open('file.txt') as json_data:
@@ -57,8 +57,8 @@ def _assert_greater(self, actual, minimum):
             raise Exception(text.format(minimum, actual))
 
     def _check_integration_data(self):
-        string = u'Palindromics numbers remain the same when ' \
-                 u'its digits are reversed'
+        string = (u'"Palindromics numbers remain the same when its digits are '
+                  u'reversed"')
         data = self.search_source(string)
 
         self._assert_greater(len(data), 1)

integration-tests/run.py

@@ -123,7 +123,7 @@ def read_parameters():
         'localhost': 'http://localhost:8080/',
         'dev': 'http://www.softcatala.org/recursos/dev/',
         'preprod': 'http://www.softcatala.org/recursos/preprod/',
-        'prod': 'http://www.softcatala.org/recursos/'
+        'prod': 'http://www.softcatala.org/recursos/',
     }
 
     opt_enviroments = "localhost, dev, prepod, prod"

src/builder.py

@@ -2,6 +2,7 @@
 # -*- coding: utf-8 -*-
 #
 # Copyright (c) 2012 Jordi Mas i Hernandez <jmas@softcatala.org>
+# Copyright (c) 2014 Leandro Regueiro Iglesias <leandro.regueiro@gmail.com>
 #
 # This program is free software; you can redistribute it and/or
 # modify it under the terms of the GNU Lesser General Public
@@ -119,10 +120,10 @@ def read_parameters():
 
 
 def load_projects_from_json():
+    global softcatala_only
+
     json = JsonBackend(projects_json)
     json.load()
-
-    global softcatala_only
 
     msg = 'Projects defined in json file {0}'.format(len(json.projects))
     logging.info(msg)

src/gerritdirectoryfileset.py

@@ -38,9 +38,11 @@ def set_project(self, project):
         self.project = project
 
     def _remove_first_line_from_file(self, filename):
-        '''Garbage prefix inserted before JSON output to prevent XSSI.''' 
-        '''This prefix is ")]}'\n" and is designed to prevent a web browser''' 
-        '''from executing the response body'''
+        """Garbage prefix inserted before JSON output to prevent XSSI.
+
+        This prefix is ")]}'\n" and is designed to prevent a web browser from
+        executing the response body.
+        """
         working_file = filename + ".old"
         shutil.copy(filename, working_file)
 

src/jsonbackend.py

@@ -35,8 +35,8 @@ def __init__(self, name):
         self.filesets = []
 
     def __str__(self):
-        text = 'ProjectDTO. Name: {0}, filename: {1}, project web: {2}, ' \
-            'disabled {3}'
+        text = ('ProjectDTO. Name: {0}, filename: {1}, project web: {2}, '
+                'disabled {3}')
         return text.format(self.name, self.filename, self.projectweb,
                            self.disabled)
 
@@ -52,8 +52,8 @@ def __init__(self):
         self.pattern = ''
 
     def __str__(self):
-        text = 'FileSetDTO. Name: {0}, url: {1}, type: {2}, excluded: {3}, ' \
-            'target: {4}, pattern: {5}'
+        text = ('FileSetDTO. Name: {0}, url: {1}, type: {2}, excluded: {3}, '
+                'target: {4}, pattern: {5}')
         return text.format(self.name, self.url, self.type, self.excluded,
                            self.target, self.pattern)
 
@@ -88,7 +88,7 @@ def _process_file_set_attributes(self, fileset, fileset_value):
             elif fileset_properties_attr == 'pattern':
                 fileset.pattern = fileset_properties_value
             else:
-                msg = 'Field \'{0}\' not recognized'
+                msg = "Field '{0}' not recognized"
                 logging.error(msg.format(fileset_properties_attr))
 
     def load(self):

src/projectmetadatadao.py

@@ -29,13 +29,16 @@ def __init__(self):
 
     def create_model(self):
         c = self.connection.cursor()
-
-        command = '''create table if not exists projects (name text primary key,  \
-                  last_fetch timestamp, last_translation_update timestamp, \
-                  words integer, checksum text);'''
+        command = ('CREATE TABLE IF NOT EXISTS projects ('
+                   'name TEXT PRIMARY KEY,'
+                   'last_fetch TIMESTAMP,'
+                   'last_translation_update TIMESTAMP,'
+                   'words INTEGER,'
+                   'checksum TEXT'
+                   ');')
         c.execute(command)
 
-        command = '''create index if not exists [ix_name] on [projects] ([name]);'''
+        command = 'CREATE INDEX IF NOT EXISTS [ix_name] ON [projects] ([name]);'
         c.execute(command)
         self.connection.commit()
 
@@ -46,16 +49,16 @@ def open(self, database_name):
 
     def put(self, dto):
         c = self.connection.cursor()
-        command = u"insert or replace into 'projects' values ('{0}', '{1}', '{2}', {3}, '{4}');". \
-                  format(dto.name, dto.last_fetch, dto.last_translation_update,
-                  dto.words, dto.checksum)
-
+        command = (u"INSERT OR REPLACE INTO 'projects' VALUES ('{0}', '{1}', "
+                   u"'{2}', {3}, '{4}');".format(dto.name, dto.last_fetch,
+                                                 dto.last_translation_update,
+                                                 dto.words, dto.checksum))
         c.execute(command)
         self.connection.commit()
 
     def get(self, name):
         c = self.connection.cursor()
-        command = u'SELECT * FROM projects where name=\'{0}\''.format(name)
+        command = u"SELECT * FROM projects WHERE name='{0}'".format(name)
         result = c.execute(command)
         row = result.fetchone()
 

src/projectmetadatadto.py

@@ -52,7 +52,7 @@ def last_fetch(self, value):
         self._last_fetch = value
 
     def __str__(self):
-        text = 'ProjectMetaDataDto. Name: {0}, last_translation_update: {1}, ' \
-            'last_fetch: {2}, words {3}'
-        return text.format(self.name, self._last_translation_update, 
-                          self._last_fetch, self.words)
+        text = ('ProjectMetaDataDto. Name: {0}, last_translation_update: {1}, '
+                'last_fetch: {2}, words {3}')
+        return text.format(self.name, self._last_translation_update,
+                           self._last_fetch, self.words)

src/projects.py

@@ -2,6 +2,7 @@
 # -*- coding: utf-8 -*-
 #
 # Copyright (c) 2012 Jordi Mas i Hernandez <jmas@softcatala.org>
+# Copyright (c) 2014 Leandro Regueiro Iglesias <leandro.regueiro@gmail.com>
 #
 # This program is free software; you can redistribute it and/or
 # modify it under the terms of the GNU Lesser General Public
@@ -85,8 +86,7 @@ def create_tm_for_all_projects(self):
                 backup_file = 'tm-previous.po'
                 shutil.copy(self.tm_file, backup_file)
                 cmd = 'msgcat -tutf-8 --use-first -o {0} {1} {2} 2> /dev/null'
-                os.system(cmd.format(self.tm_file,
-                                     backup_file,
+                os.system(cmd.format(self.tm_file, backup_file,
                                      project.get_filename()))
                 os.remove(backup_file)
             else:

src/subversionfileset.py

@@ -25,14 +25,12 @@
 class SubversionFileSet(FileSet):
 
     def do(self):
-
         if len(self.filename) == 0:
-            CMD = 'cd {0} && svn co --trust-server-cert ' \
-                '--non-interactive {1}'
+            CMD = 'cd {0} && svn co --trust-server-cert --non-interactive {1}'
         else:
             # Single file checkout
-            CMD = 'cd {0} && svn export --trust-server-cert ' \
-                '--non-interactive {1}'
+            CMD = ('cd {0} && svn export --trust-server-cert '
+                   '--non-interactive {1}')
 
         self.create_tmp_directory()
         cmd = CMD.format(self.temp_dir, self.url)

src/terminology/corpus.py

@@ -2,6 +2,7 @@
 # -*- encoding: utf-8 -*-
 #
 # Copyright (c) 2013 Jordi Mas i Hernandez <jmas@softcatala.org>
+# Copyright (c) 2014 Leandro Regueiro Iglesias <leandro.regueiro@gmail.com>
 #
 # This program is free software; you can redistribute it and/or
 # modify it under the terms of the GNU Lesser General Public
@@ -25,10 +26,11 @@
 
 
 class Corpus(object):
-    '''Loads different PO files that build the corpus'''
-    '''Strings that are not suitable candidates are discarded'''
-    '''We do a minimum clean up of strings'''
+    """Loads different PO files that build the corpus.
 
+    Strings that are not suitable candidates are discarded. We do a minimum
+    clean up of strings.
+    """
     def __init__(self, directory):
         self.directory = directory
         self.source_words = set()
@@ -44,8 +46,7 @@ def _read_stop_words(self, stopwords_file):
             line = stopwords_file.readline()
             if not line:
                 break
-            word = line.strip()
-            word = word.lower()
+            word = line.strip().lower()
             self.stop_words.add(word)
 
     def _clean_string(self, result):
@@ -56,9 +57,8 @@ def _clean_string(self, result):
         for c in CHARS:
             result = result.replace(c, '')
 
-        #remove all the leading and trailing whitespace characters
-        result = result.strip()
-        result = result.lower()
+        # Remove all the leading and trailing whitespace characters.
+        result = result.strip().lower()
         return result
 
     def _should_select_string(self, source, target):

src/terminology/glossary.py

@@ -2,6 +2,7 @@
 # -*- encoding: utf-8 -*-
 #
 # Copyright (c) 2014 Jordi Mas i Hernandez <jmas@softcatala.org>
+# Copyright (c) 2014 Leandro Regueiro Iglesias <leandro.regueiro@gmail.com>
 #
 # This program is free software; you can redistribute it and/or
 # modify it under the terms of the GNU Lesser General Public
@@ -22,7 +23,7 @@
 
 
 class Glossary(object):
-    '''Represents all the data need to generate a glossary'''
+    """Represents all the data need to generate a glossary."""
 
     def __init__(self):
         self.date = datetime.date.today().strftime("%d/%m/%Y")

src/terminology/glossaryentry.py

@@ -2,6 +2,7 @@
 # -*- encoding: utf-8 -*-
 #
 # Copyright (c) 2014 Jordi Mas i Hernandez <jmas@softcatala.org>
+# Copyright (c) 2014 Leandro Regueiro Iglesias <leandro.regueiro@gmail.com>
 #
 # This program is free software; you can redistribute it and/or
 # modify it under the terms of the GNU Lesser General Public
@@ -20,12 +21,12 @@
 
 
 class GlossaryEntry(object):
-    '''Represents an entry to be written in a glossary'''
+    """Represents an entry to be written in a glossary."""
 
     def __init__(self):
         self.source_term = u''
         self.translations = []
-        self.percentage = 0  # Percentage of frequency across all options
+        self.percentage = 0  # Percentage of frequency across all options.
 
     def get_dict(self):
         translations = []

src/terminology/referencesources.py

@@ -29,8 +29,10 @@ def __init__(self, name, short_name):
 
 
 class ReferenceSources(object):
-    '''Loads different PO files that we use as reference sources'''
-    '''like TERMCAT or Microsoft glossaries'''
+    """Loads different PO files that we use as reference sources.
+
+    Like TERMCAT or Microsoft glossaries.
+    """
     def __init__(self):
         self.stop_words = set()
         self.references = []

src/terminology/term-extract.py

@@ -44,7 +44,8 @@
 
 
 def process_projects():
-    global glossary_file, glossary_description
+    global glossary_description
+    global glossary_file
 
     corpus = Corpus(src_directory)
     corpus.process()
@@ -57,7 +58,8 @@ def process_projects():
 
     # Select terms
     MAX_TERMS = 1000
-    sorted_terms_by_tfxdf = sorted(metrics.tfxdf, key=metrics.tfxdf.get, reverse=True)
+    sorted_terms_by_tfxdf = sorted(metrics.tfxdf, key=metrics.tfxdf.get,
+                                   reverse=True)
 
     # Developer report
     glossary_entries = OrderedDict()
@@ -68,7 +70,8 @@ def process_projects():
         glossary_entries[term] = translations.create_for_word_sorted_by_frequency(corpus.documents, term, reference_sources)
 
     dev_glossary_serializer = DevGlossarySerializer()
-    dev_glossary_serializer.create(u"dev-" + glossary_file + ".html", glossary_description, corpus,
+    dev_glossary_serializer.create(u"dev-" + glossary_file + ".html",
+                                   glossary_description, corpus,
                                    glossary_entries, reference_sources)
 
     # User report
@@ -125,9 +128,8 @@ def init_logging():
 
 def using():
     usage=resource.getrusage(resource.RUSAGE_SELF)
-    return '''usertime=%s systime=%s mem=%s mb
-           '''%(usage[0],usage[1],
-                (usage[2]*resource.getpagesize())/1000000.0)
+    return ("usertime=%s systime=%s mem=%s mb" % (usage[0],usage[1],
+            (usage[2]*resource.getpagesize())/1000000.0))
 
 
 def main():

src/terminology/termcat/term-to-po.py

@@ -83,8 +83,7 @@ def main():
                 continue
 
             stored_terms[source] = translation
-            entry = polib.POEntry(msgid=source,
-                                  msgstr=translation)
+            entry = polib.POEntry(msgid=source, msgstr=translation)
             pofile.append(entry)
             terms += 1
 

src/terminology/translations.py

@@ -44,7 +44,8 @@ class Translations(object):
     '''for the glossary, grouping same translation units and sorting them by'''
     '''frequency'''
 
-    def _add_reference_translations(self, term, reference_sources, translations):
+    def _add_reference_translations(self, term, reference_sources,
+                                    translations):
 
         # Translations from references (TERMCAT only for now)
         reference_translations = reference_sources.get_translations_for_term_in_reference(term, 't')
@@ -73,7 +74,8 @@ def _add_reference_translations(self, term, reference_sources, translations):
 
         return translations_with_references
 
-    def create_for_word_sorted_by_frequency(self, documents, term, reference_sources):
+    def create_for_word_sorted_by_frequency(self, documents, term,
+                                            reference_sources):
         translations = {} # key: english keyword -> value: list of translation objects
         for document_key_filename in documents.keys():
             if term not in documents[document_key_filename]:

src/tests/testbazaarfileset.py

@@ -30,7 +30,8 @@ def test_has_filename_filename(self):
         self.assertTrue(bazaar._has_filename())
 
     def test_has_filename_path(self):
-        bazaar = BazaarFileSet('project none', 'filesetname', 'lp:~mailman-l10n-ca/', 'none.po')
+        bazaar = BazaarFileSet('project none', 'filesetname',
+                               'lp:~mailman-l10n-ca/', 'none.po')
         self.assertFalse(bazaar._has_filename())
 
 

src/transifexhubfileset.py

@@ -119,11 +119,8 @@ def _get_base_url(self, url):
     def _download_page(self):
         request = urllib2.Request(self.url)
         handle = urllib2.build_opener()
-        self.content = unicode(
-            handle.open(request).read(),
-            'utf-8',
-            errors='replace'
-        )
+        self.content = unicode(handle.open(request).read(), 'utf-8',
+                               errors='replace')
 
     def _process_options(self):
         parser = OptionsExtractor(self.url)