From 879510da82d0b4f2db4f809d6c7eca4d86ab06e4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=9E=97=E6=AA=8E?= Date: Thu, 2 Mar 2017 22:57:02 +0800 Subject: [PATCH] Upload support detection of language --- cps/book_formats.py | 4 ++-- cps/db.py | 2 +- cps/epub.py | 21 +++++++++++++++------ cps/fb2.py | 2 +- cps/web.py | 18 +++++++++++++++++- 5 files changed, 36 insertions(+), 11 deletions(-) diff --git a/cps/book_formats.py b/cps/book_formats.py index e2911561..a88e5e0e 100644 --- a/cps/book_formats.py +++ b/cps/book_formats.py @@ -64,7 +64,7 @@ def default_meta(tmp_file_path, original_file_name, original_file_extension): tags="", series="", series_id="", - languages=None) + languages="") def pdf_meta(tmp_file_path, original_file_name, original_file_extension): @@ -93,7 +93,7 @@ def pdf_meta(tmp_file_path, original_file_name, original_file_extension): tags="", series="", series_id="", - languages=None) + languages="") def pdf_preview(tmp_file_path, tmp_dir): diff --git a/cps/db.py b/cps/db.py index f25848c7..9c48cfbb 100755 --- a/cps/db.py +++ b/cps/db.py @@ -247,7 +247,7 @@ class Books(Base): identifiers = relationship('Identifiers', backref='books') def __init__(self, title, sort, author_sort, timestamp, pubdate, series_index, last_modified, path, has_cover, - authors, tags): + authors, tags, languages = None): self.title = title self.sort = sort self.author_sort = author_sort diff --git a/cps/epub.py b/cps/epub.py index e3e03cca..853abcaa 100644 --- a/cps/epub.py +++ b/cps/epub.py @@ -5,7 +5,7 @@ import zipfile from lxml import etree import os import uploader - +from iso639 import languages as isoLanguages def extractCover(zip, coverFile, coverpath, tmp_file_name): if coverFile is None: @@ -47,6 +47,15 @@ def get_epub_info(tmp_file_path, original_file_name, original_file_extension): epub_metadata[s] = p.xpath('dc:%s/text()' % s, namespaces=ns)[0] else: epub_metadata[s] = "Unknown" + #detect lang need futher modification in web.py /upload + lang = p.xpath('dc:language/text()', namespaces=ns)[0] + lang = lang.split('-', 1)[0] + if len(lang) == 2: + epub_metadata['languages'] = isoLanguages.get(part1=lang).name + elif len(lang) == 3: + epub_metadata['languages'] = isoLanguages.get(part3=lang).name + else: + epub_metadata['languages'] = "" coversection = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='cover-image']/@href", namespaces=ns) if len(coversection) > 0: @@ -59,16 +68,16 @@ def get_epub_info(tmp_file_path, original_file_name, original_file_extension): markup = zip.read(os.path.join(coverpath,coversection[0])) markupTree = etree.fromstring(markup) #no matter xhtml or html with no namespace - imgsrc = markupTree.xpath( "//*[local-name() = 'img']/@src") + imgsrc = markupTree.xpath("//*[local-name() = 'img']/@src") #imgsrc maybe startwith "../"" so fullpath join then relpath to cwd - filename = os.path.relpath(os.path.join(os.path.dirname(os.path.join(coverpath,coversection[0])),imgsrc[0])) - coverfile = extractCover(zip, filename, "", tmp_file_path) + filename = os.path.relpath(os.path.join(os.path.dirname(os.path.join(coverpath, coversection[0])), imgsrc[0])) + coverfile = extractCover(zip, filename, "", tmp_file_path) else: coverfile = extractCover(zip, coversection[0], coverpath, tmp_file_path) else: meta_cover = tree.xpath("/pkg:package/pkg:metadata/pkg:meta[@name='cover']/@content", namespaces=ns) if len(meta_cover) > 0: - meta_cover_content = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='"+meta_cover[0]+"']/@href",namespaces=ns) + meta_cover_content = tree.xpath("/pkg:package/pkg:manifest/pkg:item[@id='"+meta_cover[0]+"']/@href", namespaces=ns) if len(meta_cover_content) > 0: coverfile = extractCover(zip, meta_cover_content[0], coverpath, tmp_file_path) else: @@ -89,4 +98,4 @@ def get_epub_info(tmp_file_path, original_file_name, original_file_extension): tags="", series="", series_id="", - languages=None) + languages=epub_metadata['languages']) diff --git a/cps/fb2.py b/cps/fb2.py index 98aefdeb..7f0bf2af 100644 --- a/cps/fb2.py +++ b/cps/fb2.py @@ -60,4 +60,4 @@ def get_fb2_info(tmp_file_path, original_file_extension): tags="", series="", series_id="", - languages=None) + languages="") diff --git a/cps/web.py b/cps/web.py index 680b534e..566e6fce 100755 --- a/cps/web.py +++ b/cps/web.py @@ -2209,16 +2209,32 @@ def upload(): else: db_author = db.Authors(author, helper.get_sorted_author(author), "") db.session.add(db_author) + + #add language actually one value in list + input_language = meta.languages + db_language = None + if input_language != "": + input_language = isoLanguages.get(name=input_language).part3 + hasLanguage = db.session.query(db.Languages).filter(db.Languages.lang_code == input_language).first() + if hasLanguage: + db_language = hasLanguage + else: + db_language = db.Languages(input_language) + db.session.add(db_language) # combine path and normalize path from windows systems path = os.path.join(author_dir, title_dir).replace('\\','/') db_book = db.Books(title, "", db_author.sort, datetime.datetime.now(), datetime.datetime(101, 01, 01), 1, - datetime.datetime.now(), path, has_cover, db_author, []) + datetime.datetime.now(), path, has_cover, db_author, [], db_language) db_book.authors.append(db_author) + if db_language is not None: + db_book.languages.append(db_language) db_data = db.Data(db_book, meta.extension.upper()[1:], file_size, data_name) db_book.data.append(db_data) db.session.add(db_book) db.session.commit() + if db_language is not None: #display Full name instead of iso639.part3 + db_book.languages[0].language_name = meta.languages author_names = [] for author in db_book.authors: author_names.append(author.name)