feat: Added the ability to translate filename and metadata. resolved #…

…216

advanced.py

@@ -235,9 +235,7 @@ def show_advanced(self):
 
 
 class AdvancedTranslation(QDialog):
-    raw_text = pyqtSignal(str)
-    original_text = pyqtSignal(str)
-    translation_text = pyqtSignal((), (str,))
+    paragraph_sig = pyqtSignal(Paragraph)
     progress_bar = pyqtSignal()
 
     preparation_thread = QThread()
@@ -504,8 +502,7 @@ def terminate_translation():
         def terminate_finished():
             stop_button.setDisabled(False)
             stop_button.setText(_('Stop'))
-            self.translation_text[str].emit(
-                self.table.current_paragraph().translation)
+            self.paragraph_sig.emit(self.table.current_paragraph())
         self.trans_worker.finished.connect(terminate_finished)
 
         stack = QStackedWidget()
@@ -565,11 +562,18 @@ def layout_control(self):
         ebook_title.setCursorPosition(0)
         output_format = OutputFormat()
         output_format.setFixedWidth(150)
-        save_layout.addWidget(QLabel(_('Title')))
+        save_layout.addWidget(QLabel(_('Filename')))
         save_layout.addWidget(ebook_title, 1)
+        save_layout.addWidget(QLabel(_('Format')))
         save_layout.addWidget(output_format)
         save_layout.addWidget(save_ebook)
 
+        if self.config.get('to_library'):
+            ebook_title.setDisabled(True)
+            ebook_title.setToolTip(_(
+                "The ebook's filename is automatically managed by Calibre "
+                'according to metadata since the output path is set to '
+                'Calibre Library.'))
         ebook_title.textChanged.connect(self.ebook.set_title)
 
         layout.addWidget(cache_group)
@@ -662,10 +666,12 @@ def layout_review(self):
         translation_text.cursorPositionChanged.connect(
             translation_text.ensureCursorVisible)
 
-        self.raw_text.connect(raw_text.setPlainText)
-        self.original_text.connect(original_text.setPlainText)
-        self.translation_text.connect(translation_text.clear)
-        self.translation_text[str].connect(translation_text.setPlainText)
+        def refresh_translation(paragraph):
+            translation_text.clear()
+            raw_text.setPlainText(paragraph.raw)
+            original_text.setPlainText(paragraph.original)
+            translation_text.setPlainText(paragraph.translation)
+        self.paragraph_sig.connect(refresh_translation)
         self.trans_worker.start.connect(
             lambda: translation_text.setReadOnly(False))
         self.trans_worker.finished.connect(
@@ -715,25 +721,21 @@ def change_selected_item():
             paragraph = self.table.current_paragraph()
             if paragraph is None:
                 return
-            self.raw_text.emit(paragraph.raw)
-            self.original_text.emit(paragraph.original.strip())
-            self.translation_text[str].emit(paragraph.translation)
+            self.paragraph_sig.emit(paragraph)
         self.table.itemSelectionChanged.connect(change_selected_item)
         self.table.setCurrentItem(self.table.item(0, 0))
         change_selected_item()
 
         def translation_callback(paragraph):
             self.table.row.emit(paragraph.row)
-            self.raw_text.emit(paragraph.raw)
-            self.original_text.emit(paragraph.original)
-            self.translation_text[str].emit(paragraph.translation)
+            self.paragraph_sig.emit(paragraph)
             self.cache.update_paragraph(paragraph)
             self.progress_bar.emit()
         self.trans_worker.callback.connect(translation_callback)
 
         def streaming_translation(data):
             if data == '':
-                self.translation_text.emit()
+                self.paragraph_sig.emit(self.table.current_paragraph())
             elif isinstance(data, Paragraph):
                 self.table.setCurrentItem(self.table.item(data.row, 0))
             else:

lib/conversion.py

@@ -15,8 +15,8 @@
 from .utils import log, sep, uid, open_path
 from .cache import get_cache, TranslationCache
 from .element import (
-    get_srt_elements, get_toc_elements, get_page_elements, get_element_handler,
-    Extraction)
+    Extraction, get_element_handler, get_srt_elements, get_toc_elements,
+    get_page_elements, get_metadata_elements)
 from .translation import get_translator, get_translation
 
 
@@ -36,6 +36,7 @@ def extract_book(input_path):
     plumber = Plumber(input_path, output_path, log=log)
 
     def convert(self, oeb, output_path, input_plugin, opts, log):
+        elements.extend(get_metadata_elements(oeb.metadata))
         elements.extend(get_toc_elements(oeb.toc.nodes, []))
         elements.extend(get_page_elements(oeb.manifest.items))
     plumber.output_plugin.convert = MethodType(convert, plumber.output_plugin)
@@ -117,6 +118,8 @@ def convert(self, oeb, output_path, input_plugin, opts, log):
         log.info(debug_info)
         translation.set_progress(self.report_progress)
 
+        elements.extend(get_metadata_elements(oeb.metadata))
+        # The number of elements may vary with format conversion.
         elements.extend(get_toc_elements(oeb.toc.nodes, []))
         elements.extend(get_page_elements(oeb.manifest.items))
         original_group = element_handler.prepare_original(elements)

lib/element.py

@@ -83,6 +83,31 @@ def add_translation(
         return self.element
 
 
+class MetadataElement(Element):
+    def get_raw(self):
+        return self.element.content
+
+    def get_text(self):
+        return self.element.content
+
+    def get_content(self, placeholder):
+        return self.element.content
+
+    def add_translation(
+            self, translation, placeholder, position, translation_lang=None,
+            original_color=None, translation_color=None):
+        if translation is not None:
+            if position == 'only':
+                self.element.content = translation
+            elif position in ['above', 'left']:
+                self.element.content = '%s %s' % (
+                    translation, self.element.content)
+            else:
+                self.element.content = '%s %s' %(
+                    self.element.content, translation)
+        return self.element
+
+
 class TocElement(Element):
     def get_raw(self):
         return self.element.title
@@ -104,9 +129,9 @@ def add_translation(
 
 
 class PageElement(Element):
-    def _get_descendents(self, tags):
+    def _get_descendents(self, element, tags):
         xpath = './/*[%s]' % ' or '.join(['self::x:%s' % tag for tag in tags])
-        return self._element_copy().xpath(xpath, namespaces=ns)
+        return element.xpath(xpath, namespaces=ns)
 
     def get_name(self):
         return get_name(self.element)
@@ -125,13 +150,15 @@ def delete(self):
         self.element.getparent().remove(self.element)
 
     def get_content(self, placeholder):
-        for noise in self._get_descendents(('rt', 'rp', 'sup', 'sub')):
+        element_copy = self._element_copy()
+        for noise in self._get_descendents(
+                element_copy, ('rt', 'rp', 'sup', 'sub')):
             parent = noise.getparent()
             parent.text = (parent.text or '') + (noise.tail or '')
             parent.remove(noise)
 
         self.reserve_elements = self._get_descendents(
-            ('img', 'code', 'br', 'hr', 'sub', 'sup', 'kbd'))
+            element_copy, ('img', 'code', 'br', 'hr', 'sub', 'sup', 'kbd'))
         count = 0
         for reserve in self.reserve_elements:
             replacement = placeholder[0].format(format(count, '05'))
@@ -146,7 +173,7 @@ def get_content(self, placeholder):
             parent.remove(reserve)
             count += 1
 
-        return trim(''.join(self._element_copy().itertext()))
+        return trim(''.join(element_copy.itertext()))
 
     def _polish_translation(self, translation):
         translation = translation.replace('\n', '<br />')
@@ -513,6 +540,22 @@ def get_srt_elements(path):
     return [SrtElement(section) for section in sections]
 
 
+def get_metadata_elements(metadata):
+    elements = []
+    names = (
+        'title', 'creator', 'publisher', 'rights', 'subject', 'contributor')
+    pattern = re.compile(r'[a-z]+')
+    for key in metadata.iterkeys():
+        if key not in names:
+            continue
+        items = getattr(metadata, key)
+        for item in items:
+            if pattern.search(item.content) is None:
+                continue
+            elements.append(MetadataElement(item, 'content.opf'))
+    return elements
+
+
 def get_toc_elements(nodes, elements=[]):
     """Be aware that elements should not overlap with existing data."""
     for node in nodes:

tests/test_cache.py

@@ -14,7 +14,6 @@ def test_created_paragraph(self):
         self.assertFalse(self.paragraph.is_cache)
         self.assertIsNone(self.paragraph.error)
         self.assertTrue(self.paragraph.aligned)
-        self.assertIsNone(self.paragraph.background)
 
     def test_get_attributes(self):
         self.assertEqual({'class': 'test'}, self.paragraph.get_attributes())

tests/test_element.py

@@ -3,13 +3,14 @@
 
 from lxml import etree
 
-from calibre.ebooks.oeb.base import TOC
+from calibre.ebooks.oeb.base import TOC, Metadata
 
 from ..lib.utils import ns
 from ..lib.cache import Paragraph
 from ..lib.element import (
-    get_string, get_name, SrtElement, TocElement, PageElement, Extraction,
-    ElementHandler, ElementHandlerMerge, get_toc_elements)
+    get_string, get_name, Extraction, ElementHandler, ElementHandlerMerge,
+    SrtElement, TocElement, PageElement, MetadataElement, get_toc_elements,
+    get_metadata_elements)
 from ..engines import DeeplFreeTranslate
 from ..engines.base import Base
 
@@ -45,6 +46,22 @@ def test_get_toc_elements(self):
         elements = get_toc_elements(toc, [])
         self.assertEqual(3, len(elements))
 
+    def test_get_metadata_elements(self):
+        metadata = Mock(Metadata)
+        item_1 = Mock(Metadata.Item, content='a')
+        item_2 = Mock(Metadata.Item, content='b')
+        item_3 = Mock(Metadata.Item, content='0')
+        metadata.title = [item_1]
+        metadata.subject = [item_2, item_3]
+        metadata.language = []
+        metadata.iterkeys.return_value = ['title', 'subject', 'language']
+
+        elements = get_metadata_elements(metadata)
+
+        self.assertEqual(2, len(elements))
+        self.assertIs(item_1, elements[0].element)
+        self.assertIs(item_2, elements[1].element)
+
 
 class TestSrtElement(unittest.TestCase):
     def setUp(self):
@@ -84,6 +101,46 @@ def test_add_translation_only(self):
         self.assertEqual('A', element[2])
 
 
+class TestMetadataElement(unittest.TestCase):
+    def setUp(self):
+        self.medata_item = Mock(Metadata.Item, content='a')
+        self.element = MetadataElement(self.medata_item)
+
+    def test_get_raw(self):
+        self.assertEqual('a', self.element.get_raw())
+
+    def test_get_text(self):
+        self.assertEqual('a', self.element.get_text())
+
+    def test_get_content(self):
+        self.assertEqual('a', self.element.get_content(Base.placeholder))
+
+    def test_add_translation_none(self):
+        self.assertIs(
+            self.element.element,
+            self.element.add_translation(None, Base.placeholder, 'below'))
+
+    def test_add_translation_below(self):
+        element = self.element.add_translation('A', Base.placeholder, 'below')
+        self.assertEqual('a A', element.content)
+
+    def test_add_translation_right(self):
+        element = self.element.add_translation('A', Base.placeholder, 'right')
+        self.assertEqual('a A', element.content)
+
+    def test_add_translation_above(self):
+        element = self.element.add_translation('A', Base.placeholder, 'above')
+        self.assertEqual('A a', element.content)
+
+    def test_add_translation_left(self):
+        element = self.element.add_translation('A', Base.placeholder, 'left')
+        self.assertEqual('A a', element.content)
+
+    def test_add_translation_only(self):
+        element = self.element.add_translation('A', Base.placeholder, 'only')
+        self.assertEqual('A', element.content)
+
+
 class TestTocElement(unittest.TestCase):
     def setUp(self):
         self.element = TocElement(TOC('a', 'a.html'), 'toc.ncx')

translations/es.po

@@ -8,7 +8,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: Ebook Translator Calibre Plugin\n"
 "Report-Msgid-Bugs-To: [email protected]\n"
-"POT-Creation-Date: 2024-03-10 12:31+0800\n"
+"POT-Creation-Date: 2024-03-11 21:06+0800\n"
 "PO-Revision-Date: 2023-04-17 14:17+0800\n"
 "Last-Translator: Automatically generated\n"
 "Language-Team: none\n"
@@ -109,8 +109,16 @@ msgstr ""
 msgid "Output"
 msgstr ""
 
-msgid "Title"
-msgstr "Título"
+msgid "Filename"
+msgstr ""
+
+msgid "Format"
+msgstr ""
+
+msgid ""
+"The ebook's filename is automatically managed by Calibre according to "
+"metadata since the output path is set to Calibre Library."
+msgstr ""
 
 msgid "Translated"
 msgstr ""
@@ -148,6 +156,9 @@ msgstr ""
 msgid "Output Format"
 msgstr "Formato de salida"
 
+msgid "Title"
+msgstr "Título"
+
 msgid "Translate"
 msgstr "Traducir"
 
@@ -206,9 +217,6 @@ msgstr ""
 msgid "Merge Length"
 msgstr ""
 
-msgid "Filename"
-msgstr ""
-
 msgid "Size (MB)"
 msgstr ""