openlp-core team mailing list archive

[Tomas Groth <tomasgroth@xxxxxxxx>]

Tomas Groth has proposed merging lp:~tomasgroth/openlp/webbibles into lp:openlp.

Requested reviews:
  OpenLP Core (openlp-core)

For more details, see:
https://code.launchpad.net/~tomasgroth/openlp/webbibles/+merge/251175

Get the list of web-bibles from the websites, instead of using a static db.
-- 
Your team OpenLP Core is requested to review the proposed merge of lp:~tomasgroth/openlp/webbibles into lp:openlp.

=== modified file 'openlp/plugins/bibles/forms/bibleimportform.py'
--- openlp/plugins/bibles/forms/bibleimportform.py	2015-01-20 21:38:34 +0000
+++ openlp/plugins/bibles/forms/bibleimportform.py	2015-02-26 21:16:14 +0000
@@ -24,6 +24,7 @@
 """
 import logging
 import os
+import urllib.error
 
 from PyQt4 import QtGui
 
@@ -34,6 +35,7 @@
 from openlp.core.utils import get_locale_key
 from openlp.plugins.bibles.lib.manager import BibleFormat
 from openlp.plugins.bibles.lib.db import BiblesResourcesDB, clean_filename
+from openlp.plugins.bibles.lib.http import CWExtract, BGExtract, BSExtract
 
 log = logging.getLogger(__name__)
 
@@ -90,7 +92,6 @@
         Perform any custom initialisation for bible importing.
         """
         self.manager.set_process_dialog(self)
-        self.load_Web_Bibles()
         self.restart()
         self.select_stack.setCurrentIndex(0)
 
@@ -104,6 +105,7 @@
         self.csv_verses_button.clicked.connect(self.on_csv_verses_browse_button_clicked)
         self.open_song_browse_button.clicked.connect(self.on_open_song_browse_button_clicked)
         self.zefania_browse_button.clicked.connect(self.on_zefania_browse_button_clicked)
+        self.web_update_button.clicked.connect(self.on_web_update_button_clicked)
 
     def add_custom_pages(self):
         """
@@ -202,20 +204,33 @@
         self.web_bible_tab.setObjectName('WebBibleTab')
         self.web_bible_layout = QtGui.QFormLayout(self.web_bible_tab)
         self.web_bible_layout.setObjectName('WebBibleLayout')
+        self.web_update_label = QtGui.QLabel(self.web_bible_tab)
+        self.web_update_label.setObjectName('WebUpdateLabel')
+        self.web_bible_layout.setWidget(0, QtGui.QFormLayout.LabelRole, self.web_update_label)
+        self.web_update_button = QtGui.QPushButton(self.web_bible_tab)
+        self.web_update_button.setObjectName('WebUpdateButton')
+        self.web_bible_layout.setWidget(0, QtGui.QFormLayout.FieldRole, self.web_update_button)
         self.web_source_label = QtGui.QLabel(self.web_bible_tab)
         self.web_source_label.setObjectName('WebSourceLabel')
-        self.web_bible_layout.setWidget(0, QtGui.QFormLayout.LabelRole, self.web_source_label)
+        self.web_bible_layout.setWidget(1, QtGui.QFormLayout.LabelRole, self.web_source_label)
         self.web_source_combo_box = QtGui.QComboBox(self.web_bible_tab)
         self.web_source_combo_box.setObjectName('WebSourceComboBox')
         self.web_source_combo_box.addItems(['', '', ''])
-        self.web_bible_layout.setWidget(0, QtGui.QFormLayout.FieldRole, self.web_source_combo_box)
+        self.web_source_combo_box.setEnabled(False)
+        self.web_bible_layout.setWidget(1, QtGui.QFormLayout.FieldRole, self.web_source_combo_box)
         self.web_translation_label = QtGui.QLabel(self.web_bible_tab)
         self.web_translation_label.setObjectName('web_translation_label')
-        self.web_bible_layout.setWidget(1, QtGui.QFormLayout.LabelRole, self.web_translation_label)
+        self.web_bible_layout.setWidget(2, QtGui.QFormLayout.LabelRole, self.web_translation_label)
         self.web_translation_combo_box = QtGui.QComboBox(self.web_bible_tab)
         self.web_translation_combo_box.setSizeAdjustPolicy(QtGui.QComboBox.AdjustToContents)
         self.web_translation_combo_box.setObjectName('WebTranslationComboBox')
-        self.web_bible_layout.setWidget(1, QtGui.QFormLayout.FieldRole, self.web_translation_combo_box)
+        self.web_translation_combo_box.setEnabled(False)
+        self.web_bible_layout.setWidget(2, QtGui.QFormLayout.FieldRole, self.web_translation_combo_box)
+        self.web_progress_bar = QtGui.QProgressBar(self)
+        self.web_progress_bar.setRange(0, 3)
+        self.web_progress_bar.setObjectName('WebTranslationProgressBar')
+        self.web_progress_bar.setVisible(False)
+        self.web_bible_layout.setWidget(3, QtGui.QFormLayout.SpanningRole, self.web_progress_bar)
         self.web_tab_widget.addTab(self.web_bible_tab, '')
         self.web_proxy_tab = QtGui.QWidget()
         self.web_proxy_tab.setObjectName('WebProxyTab')
@@ -314,6 +329,8 @@
         self.open_song_file_label.setText(translate('BiblesPlugin.ImportWizardForm', 'Bible file:'))
         self.web_source_label.setText(translate('BiblesPlugin.ImportWizardForm', 'Location:'))
         self.zefania_file_label.setText(translate('BiblesPlugin.ImportWizardForm', 'Bible file:'))
+        self.web_update_label.setText(translate('BiblesPlugin.ImportWizardForm', 'Click to download bible list'))
+        self.web_update_button.setText(translate('BiblesPlugin.ImportWizardForm', 'Download bible list'))
         self.web_source_combo_box.setItemText(WebDownload.Crosswalk, translate('BiblesPlugin.ImportWizardForm',
                                                                                'Crosswalk'))
         self.web_source_combo_box.setItemText(WebDownload.BibleGateway, translate('BiblesPlugin.ImportWizardForm',
@@ -388,8 +405,11 @@
                     self.zefania_file_edit.setFocus()
                     return False
             elif self.field('source_format') == BibleFormat.WebDownload:
-                self.version_name_edit.setText(self.web_translation_combo_box.currentText())
-                return True
+                # If count is 0 the bible list has not yet been downloaded
+                if self.web_translation_combo_box.count() == 0:
+                    return False
+                else:
+                    self.version_name_edit.setText(self.web_translation_combo_box.currentText())
             return True
         elif self.currentPage() == self.license_details_page:
             license_version = self.field('license_version')
@@ -434,9 +454,10 @@
         :param index: The index of the combo box.
         """
         self.web_translation_combo_box.clear()
-        bibles = list(self.web_bible_list[index].keys())
-        bibles.sort(key=get_locale_key)
-        self.web_translation_combo_box.addItems(bibles)
+        if self.web_bible_list:
+            bibles = list(self.web_bible_list[index].keys())
+            bibles.sort(key=get_locale_key)
+            self.web_translation_combo_box.addItems(bibles)
 
     def on_osis_browse_button_clicked(self):
         """
@@ -475,6 +496,39 @@
         self.get_file_name(WizardStrings.OpenTypeFile % WizardStrings.ZEF, self.zefania_file_edit,
                            'last directory import')
 
+    def on_web_update_button_clicked(self):
+        """
+        Download list of bibles from Crosswalk, BibleServer and BibleGateway.
+        """
+        # Download from Crosswalk, BiblesGateway, BibleServer
+        self.web_bible_list = {}
+        self.web_source_combo_box.setEnabled(False)
+        self.web_translation_combo_box.setEnabled(False)
+        self.web_update_button.setEnabled(False)
+        self.web_progress_bar.setVisible(True)
+        self.web_progress_bar.setValue(0)
+        proxy_server = self.field('proxy_server')
+        for (download_type, extractor) in ((WebDownload.Crosswalk, CWExtract(proxy_server)),
+                                           (WebDownload.BibleGateway, BGExtract(proxy_server)),
+                                           (WebDownload.Bibleserver, BSExtract(proxy_server))):
+            try:
+                bibles = extractor.get_bibles_from_http()
+            except (urllib.error.URLError, ConnectionError) as err:
+                critical_error_message_box(translate('BiblesPlugin.ImportWizardForm', 'Error during download'),
+                                           translate('BiblesPlugin.ImportWizardForm',
+                                                     'An error occurred while downloading the list of bibles from %s.'))
+            self.web_bible_list[download_type] = {}
+            for (bible_name, bible_key, language_code) in bibles:
+                self.web_bible_list[download_type][bible_name] = (bible_key, language_code)
+            self.web_progress_bar.setValue(download_type + 1)
+        # Update combo box if something got into the list
+        if self.web_bible_list:
+            self.on_web_source_combo_box_index_changed(0)
+            self.web_source_combo_box.setEnabled(True)
+            self.web_translation_combo_box.setEnabled(True)
+            self.web_update_button.setEnabled(True)
+            self.web_progress_bar.setVisible(False)
+
     def register_fields(self):
         """
         Register the bible import wizard fields.
@@ -520,30 +574,6 @@
         self.on_web_source_combo_box_index_changed(WebDownload.Crosswalk)
         settings.endGroup()
 
-    def load_Web_Bibles(self):
-        """
-        Load the lists of Crosswalk, BibleGateway and Bibleserver bibles.
-        """
-        # Load Crosswalk Bibles.
-        self.load_Bible_Resource(WebDownload.Crosswalk)
-        # Load BibleGateway Bibles.
-        self.load_Bible_Resource(WebDownload.BibleGateway)
-        # Load and Bibleserver Bibles.
-        self.load_Bible_Resource(WebDownload.Bibleserver)
-
-    def load_Bible_Resource(self, download_type):
-        """
-        Loads a web bible from bible_resources.sqlite.
-
-        :param download_type: The WebDownload type e.g. bibleserver.
-        """
-        self.web_bible_list[download_type] = {}
-        bibles = BiblesResourcesDB.get_webbibles(WebDownload.Names[download_type])
-        for bible in bibles:
-            version = bible['name']
-            name = bible['abbreviation']
-            self.web_bible_list[download_type][version] = name.strip()
-
     def pre_wizard(self):
         """
         Prepare the UI for the import.
@@ -583,14 +613,15 @@
             self.progress_bar.setMaximum(1)
             download_location = self.field('web_location')
             bible_version = self.web_translation_combo_box.currentText()
-            bible = self.web_bible_list[download_location][bible_version]
+            (bible, language_id) = self.web_bible_list[download_location][bible_version]
             importer = self.manager.import_bible(
                 BibleFormat.WebDownload, name=license_version,
                 download_source=WebDownload.Names[download_location],
                 download_name=bible,
                 proxy_server=self.field('proxy_server'),
                 proxy_username=self.field('proxy_username'),
-                proxy_password=self.field('proxy_password')
+                proxy_password=self.field('proxy_password'),
+                language_id=language_id
             )
         elif bible_type == BibleFormat.Zefania:
             # Import an Zefania bible.

=== modified file 'openlp/plugins/bibles/lib/http.py'
--- openlp/plugins/bibles/lib/http.py	2015-02-06 20:29:38 +0000
+++ openlp/plugins/bibles/lib/http.py	2015-02-26 21:16:14 +0000
@@ -50,6 +50,38 @@
 }
 VERSE_NUMBER_REGEX = re.compile(r'v(\d{1,2})(\d{3})(\d{3}) verse.*')
 
+BIBLESERVER_LANGUAGE_CODE = {
+    'fl_1': 'de',
+    'fl_2': 'en',
+    'fl_3': 'fr',
+    'fl_4': 'it',
+    'fl_5': 'es',
+    'fl_6': 'pt',
+    'fl_7': 'ru',
+    'fl_8': 'sv',
+    'fl_9': 'no',
+    'fl_10': 'nl',
+    'fl_11': 'cs',
+    'fl_12': 'sk',
+    'fl_13': 'ro',
+    'fl_14': 'hr',
+    'fl_15': 'hu',
+    'fl_16': 'bg',
+    'fl_17': 'ar',
+    'fl_18': 'tr',
+    'fl_19': 'pl',
+    'fl_20': 'da',
+    'fl_21': 'zh'
+}
+
+CROSSWALK_LANGUAGES = {
+    'Portuguese': 'pt',
+    'German': 'de',
+    'Italian': 'it',
+    'Español': 'es',
+    'French': 'fr',
+    'Dutch': 'nl'
+}
 
 log = logging.getLogger(__name__)
 
@@ -222,6 +254,8 @@
         if not soup:
             return None
         div = soup.find('div', 'result-text-style-normal')
+        if not div:
+            return None
         self._clean_soup(div)
         span_list = div.find_all('span', 'text')
         log.debug('Span list: %s', span_list)
@@ -278,6 +312,42 @@
                 books.append(book.contents[0])
         return books
 
+    def get_bibles_from_http(self):
+        """
+        Load a list of bibles from BibleGateway website.
+
+        returns a list in the form [(biblename, biblekey, language_code)]
+        """
+        log.debug('BGExtract.get_bibles_from_http')
+        bible_url = 'https://legacy.biblegateway.com/versions/'
+        soup = get_soup_for_bible_ref(bible_url)
+        if not soup:
+            return None
+        bible_select = soup.find('select', {'class': 'translation-dropdown'})
+        if not bible_select:
+            log.debug('No select tags found - did site change?')
+            return None
+        option_tags = bible_select.find_all('option')
+        if not option_tags:
+            log.debug('No option tags found - did site change?')
+            return None
+        current_lang = ''
+        bibles = []
+        for ot in option_tags:
+            tag_class = ''
+            try:
+                tag_class = ot['class'][0]
+            except KeyError:
+                tag_class = ''
+            tag_text = ot.get_text()
+            if tag_class == 'lang':
+                current_lang = tag_text[tag_text.find('(') + 1:tag_text.find(')')].lower()
+            elif tag_class == 'spacer':
+                continue
+            else:
+                bibles.append((tag_text, ot['value'], current_lang))
+        return bibles
+
 
 class BSExtract(RegistryProperties):
     """
@@ -338,6 +408,43 @@
         content = content.find_all('li')
         return [book.contents[0].contents[0] for book in content if len(book.contents[0].contents)]
 
+    def get_bibles_from_http(self):
+        """
+        Load a list of bibles from Bibleserver website.
+
+        returns a list in the form [(biblename, biblekey, language_code)]
+        """
+        log.debug('BSExtract.get_bibles_from_http')
+        bible_url = 'http://www.bibleserver.com/index.php?language=2'
+        soup = get_soup_for_bible_ref(bible_url)
+        if not soup:
+            return None
+        bible_links = soup.find_all('a', {'class': 'trlCell'})
+        if not bible_links:
+            log.debug('No a tags found - did site change?')
+            return None
+        bibles = []
+        for link in bible_links:
+            bible_name = link.get_text()
+            # Skip any audio
+            if 'audio' in bible_name.lower():
+                continue
+            try:
+                bible_link = link['href']
+                bible_key = bible_link[bible_link.rfind('/') + 1:]
+                css_classes = link['class']
+            except KeyError:
+                log.debug('No href/class attribute found - did site change?')
+            language_code = ''
+            for css_class in css_classes:
+                if css_class.startswith('fl_'):
+                    try:
+                        language_code = BIBLESERVER_LANGUAGE_CODE[css_class]
+                    except KeyError:
+                        language_code = ''
+            bibles.append((bible_name, bible_key, language_code))
+        return bibles
+
 
 class CWExtract(RegistryProperties):
     """
@@ -408,6 +515,49 @@
             books.append(book.contents[0])
         return books
 
+    def get_bibles_from_http(self):
+        """
+        Load a list of bibles from Crosswalk website.
+        returns a list in the form [(biblename, biblekey, language_code)]
+        """
+        log.debug('CWExtract.get_bibles_from_http')
+        bible_url = 'http://www.biblestudytools.com/search/bible-search.part/'
+        soup = get_soup_for_bible_ref(bible_url)
+        if not soup:
+            return None
+        bible_select = soup.find('select')
+        if not bible_select:
+            log.debug('No select tags found - did site change?')
+            return None
+        option_tags = bible_select.find_all('option')
+        if not option_tags:
+            log.debug('No option tags found - did site change?')
+            return None
+        bibles = []
+        for ot in option_tags:
+            tag_text = ot.get_text().strip()
+            try:
+                tag_value = ot['value']
+            except KeyError:
+                log.exception('No value attribute found - did site change?')
+                return None
+            if not tag_value:
+                continue
+            # The names of non-english bibles has their language in parentheses at the end
+            if tag_text.endswith(')'):
+                language = tag_text[tag_text.rfind('(') + 1:-1]
+                if language in CROSSWALK_LANGUAGES:
+                    language_code = CROSSWALK_LANGUAGES[language]
+                else:
+                    language_code = ''
+            # ... except for the latin vulgate
+            elif 'latin' in tag_text.lower():
+                language_code = 'la'
+            else:
+                language_code = 'en'
+            bibles.append((tag_text, tag_value, language_code))
+        return bibles
+
 
 class HTTPBible(BibleDB, RegistryProperties):
     log.info('%s HTTPBible loaded', __name__)
@@ -428,6 +578,7 @@
         self.proxy_server = None
         self.proxy_username = None
         self.proxy_password = None
+        self.language_id = None
         if 'path' in kwargs:
             self.path = kwargs['path']
         if 'proxy_server' in kwargs:
@@ -436,6 +587,8 @@
             self.proxy_username = kwargs['proxy_username']
         if 'proxy_password' in kwargs:
             self.proxy_password = kwargs['proxy_password']
+        if 'language_id' in kwargs:
+            self.language_id = kwargs['language_id']
 
     def do_import(self, bible_name=None):
         """
@@ -468,13 +621,11 @@
             return False
         self.wizard.progress_bar.setMaximum(len(books) + 2)
         self.wizard.increment_progress_bar(translate('BiblesPlugin.HTTPBible', 'Registering Language...'))
-        bible = BiblesResourcesDB.get_webbible(self.download_name, self.download_source.lower())
-        if bible['language_id']:
-            language_id = bible['language_id']
-            self.save_meta('language_id', language_id)
+        if self.language_id:
+            self.save_meta('language_id', self.language_id)
         else:
-            language_id = self.get_language(bible_name)
-        if not language_id:
+            self.language_id = self.get_language(bible_name)
+        if not self.language_id:
             log.error('Importing books from %s failed' % self.filename)
             return False
         for book in books:
@@ -482,7 +633,7 @@
                 break
             self.wizard.increment_progress_bar(translate(
                 'BiblesPlugin.HTTPBible', 'Importing %s...', 'Importing <book name>...') % book)
-            book_ref_id = self.get_book_ref_id_by_name(book, len(books), language_id)
+            book_ref_id = self.get_book_ref_id_by_name(book, len(books), self.language_id)
             if not book_ref_id:
                 log.error('Importing books from %s - download name: "%s" failed' %
                           (self.download_source, self.download_name))

=== modified file 'tests/interfaces/openlp_plugins/bibles/test_lib_http.py'
--- tests/interfaces/openlp_plugins/bibles/test_lib_http.py	2015-01-18 13:39:21 +0000
+++ tests/interfaces/openlp_plugins/bibles/test_lib_http.py	2015-02-26 21:16:14 +0000
@@ -25,7 +25,7 @@
 from unittest import TestCase
 
 from openlp.core.common import Registry
-from openlp.plugins.bibles.lib.http import BGExtract, CWExtract
+from openlp.plugins.bibles.lib.http import BGExtract, CWExtract, BSExtract
 from tests.interfaces import MagicMock
 
 
@@ -116,3 +116,46 @@
 
         # THEN: We should get back a valid service item
         assert len(results.verse_list) == 36, 'The book of John should not have had any verses added or removed'
+
+    def bibleserver_get_bibles_test(self):
+        """
+        Test getting list of bibles from BibelServer.com
+        """
+        # GIVEN: A new Bible Server extraction class
+        handler = BSExtract()
+
+        # WHEN: downloading bible list from bibleserver
+        bibles = handler.get_bibles_from_http()
+
+        # THEN: The list should not be None, and some known bibles should be there
+        self.assertIsNotNone(bibles)
+        self.assertIn(('New Int. Readers Version', 'NIRV', 'en'), bibles)
+        self.assertIn(('Българската Библия', 'BLG', 'bg'), bibles)
+
+    def biblegateway_get_bibles_test(self):
+        """
+        Test getting list of bibles from BibelGateway.com
+        """
+        # GIVEN: A new Bible Gateway extraction class
+        handler = BGExtract()
+
+        # WHEN: downloading bible list from Crosswalk
+        bibles = handler.get_bibles_from_http()
+
+        # THEN: The list should not be None, and some known bibles should be there
+        self.assertIsNotNone(bibles)
+        self.assertIn(('Holman Christian Standard Bible', 'HCSB', 'en'), bibles)
+
+    def crosswalk_get_bibles_test(self):
+        """
+        Test getting list of bibles from Crosswalk.com
+        """
+        # GIVEN: A new Crosswalk extraction class
+        handler = CWExtract()
+
+        # WHEN: downloading bible list from Crosswalk
+        bibles = handler.get_bibles_from_http()
+
+        # THEN: The list should not be None, and some known bibles should be there
+        self.assertIsNotNone(bibles)
+        self.assertIn(('Giovanni Diodati 1649 (Italian)', 'gdb', 'it'), bibles)