This is an automated email from the ASF dual-hosted git repository.
tballison pushed a change to branch TIKA-4728-js-in-pdf
in repository https://gitbox.apache.org/repos/asf/tika.git
from daef21e3a3 TIKA-4728 - fix xhtml in widgets
add 571ffb5b23 TIKA-4728 - general xhtml fixes and tests
No new revisions were added by this update.
Summary of changes:
.../ParsingEmbeddedDocumentExtractor.java | 9 +--
.../tika/AbstractXHTMLWellFormednessTest.java | 84 ++++++++++++++++++++++
.../src/test/java/org/apache/tika/TikaTest.java | 6 ++
tika-parent/pom.xml | 23 ++++++
.../tika/parser/XHTMLWellFormednessTest.java | 7 +-
.../tika/parser/iwork/PagesContentHandler.java | 19 ++++-
.../tika/parser/iwork/XHTMLWellFormednessTest.java | 6 +-
.../parser/audiovideo/XHTMLWellFormednessTest.java | 6 +-
.../java/org/apache/tika/parser/prt/PRTParser.java | 2 +
.../tika/parser/dwg/XHTMLWellFormednessTest.java | 6 +-
.../tika/parser/code/XHTMLWellFormednessTest.java | 6 +-
.../parser/crypto/XHTMLWellFormednessTest.java | 6 +-
.../tika/parser/font/XHTMLWellFormednessTest.java | 6 +-
.../tika/parser/html/XHTMLWellFormednessTest.java | 6 +-
.../tika/parser/image/XHTMLWellFormednessTest.java | 6 +-
.../tika/parser/mail/XHTMLWellFormednessTest.java | 6 +-
.../parser/microsoft/XHTMLWellFormednessTest.java | 6 +-
.../org/apache/tika/parser/epub/EpubParser.java | 10 ++-
.../parser/miscoffice/XHTMLWellFormednessTest.java | 6 +-
.../tika/parser/feed/XHTMLWellFormednessTest.java | 6 +-
.../tika/parser/ocr/XHTMLWellFormednessTest.java | 6 +-
.../apache/tika/parser/pdf/AbstractPDF2XHTML.java | 4 +-
.../tika/parser/pdf/XHTMLWellFormednessTest.java | 6 +-
.../tika/parser/pkg/XHTMLWellFormednessTest.java | 25 ++++---
.../tika/parser/txt/XHTMLWellFormednessTest.java | 6 +-
.../tika/parser/warc/XHTMLWellFormednessTest.java | 6 +-
.../java/org/apache/tika/parser/tmx/TMXParser.java | 2 +
.../apache/tika/parser/xliff/XLIFF12Parser.java | 3 +-
.../tika/parser/xml/XHTMLWellFormednessTest.java | 6 +-
29 files changed, 220 insertions(+), 76 deletions(-)
create mode 100644
tika-core/src/test/java/org/apache/tika/AbstractXHTMLWellFormednessTest.java
copy tika-core/src/main/java/org/apache/tika/parser/RenderingParser.java =>
tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/java/org/apache/tika/parser/XHTMLWellFormednessTest.java
(86%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/test/java/org/apache/tika/parser/iwork/XHTMLWellFormednessTest.java
(82%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/test/java/org/apache/tika/parser/audiovideo/XHTMLWellFormednessTest.java
(81%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-cad-module/src/test/java/org/apache/tika/parser/dwg/XHTMLWellFormednessTest.java
(82%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-code-module/src/test/java/org/apache/tika/parser/code/XHTMLWellFormednessTest.java
(82%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-crypto-module/src/test/java/org/apache/tika/parser/crypto/XHTMLWellFormednessTest.java
(82%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-font-module/src/test/java/org/apache/tika/parser/font/XHTMLWellFormednessTest.java
(82%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/XHTMLWellFormednessTest.java
(82%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-image-module/src/test/java/org/apache/tika/parser/image/XHTMLWellFormednessTest.java
(82%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/test/java/org/apache/tika/parser/mail/XHTMLWellFormednessTest.java
(82%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/XHTMLWellFormednessTest.java
(81%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/test/java/org/apache/tika/parser/miscoffice/XHTMLWellFormednessTest.java
(81%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-news-module/src/test/java/org/apache/tika/parser/feed/XHTMLWellFormednessTest.java
(82%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/XHTMLWellFormednessTest.java
(82%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/XHTMLWellFormednessTest.java
(82%)
copy
tika-pipes/tika-pipes-plugins/tika-pipes-http/src/main/java/org/apache/tika/pipes/fetcher/http/jwt/JwtSecretCreds.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/test/java/org/apache/tika/parser/pkg/XHTMLWellFormednessTest.java
(56%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/test/java/org/apache/tika/parser/txt/XHTMLWellFormednessTest.java
(82%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/test/java/org/apache/tika/parser/warc/XHTMLWellFormednessTest.java
(82%)
copy
tika-core/src/main/java/org/apache/tika/language/detect/LanguageConfidence.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xml-module/src/test/java/org/apache/tika/parser/xml/XHTMLWellFormednessTest.java
(82%)