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 571ffb5b23 TIKA-4728 - general xhtml fixes and tests
add 155d2f6806 TIKA-4728 - add strict validation as an option
No new revisions were added by this update.
Summary of changes:
.../tika/sax/BasicContentHandlerFactory.java | 28 +++
.../org/apache/tika/sax/StrictXHTMLValidator.java | 227 +++++++++++++++++++++
.../tika/AbstractXHTMLWellFormednessTest.java | 84 --------
.../src/test/java/org/apache/tika/TikaTest.java | 61 +++---
tika-parent/pom.xml | 23 ---
.../tika/parser/XHTMLWellFormednessTest.java | 22 --
.../tika/parser/iwork/XHTMLWellFormednessTest.java | 22 --
.../parser/audiovideo/XHTMLWellFormednessTest.java | 22 --
.../tika/parser/dwg/XHTMLWellFormednessTest.java | 22 --
.../apache/tika/parser/code/SourceCodeParser.java | 25 +++
.../tika/parser/code/SourceCodeParserTest.java | 1 -
.../tika/parser/code/XHTMLWellFormednessTest.java | 22 --
.../parser/crypto/XHTMLWellFormednessTest.java | 22 --
.../tika/parser/font/XHTMLWellFormednessTest.java | 22 --
.../tika/parser/html/XHTMLWellFormednessTest.java | 22 --
.../tika/parser/image/XHTMLWellFormednessTest.java | 22 --
.../tika/parser/mail/XHTMLWellFormednessTest.java | 22 --
.../parser/microsoft/XHTMLWellFormednessTest.java | 22 --
.../parser/miscoffice/XHTMLWellFormednessTest.java | 22 --
.../tika/parser/feed/XHTMLWellFormednessTest.java | 22 --
.../tika/parser/ocr/XHTMLWellFormednessTest.java | 22 --
.../org/apache/tika/parser/pdf/PDFParserTest.java | 5 +-
.../tika/parser/pdf/XHTMLWellFormednessTest.java | 22 --
.../tika/parser/pkg/XHTMLWellFormednessTest.java | 35 ----
.../java/org/apache/tika/parser/txt/TXTParser.java | 27 ++-
.../tika/parser/txt/XHTMLWellFormednessTest.java | 22 --
.../tika/parser/warc/XHTMLWellFormednessTest.java | 22 --
.../tika/parser/xml/XHTMLWellFormednessTest.java | 22 --
28 files changed, 328 insertions(+), 584 deletions(-)
create mode 100644
tika-core/src/main/java/org/apache/tika/sax/StrictXHTMLValidator.java
delete mode 100644
tika-core/src/test/java/org/apache/tika/AbstractXHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/java/org/apache/tika/parser/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-apple-module/src/test/java/org/apache/tika/parser/iwork/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/test/java/org/apache/tika/parser/audiovideo/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-cad-module/src/test/java/org/apache/tika/parser/dwg/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-code-module/src/test/java/org/apache/tika/parser/code/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-crypto-module/src/test/java/org/apache/tika/parser/crypto/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-font-module/src/test/java/org/apache/tika/parser/font/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-image-module/src/test/java/org/apache/tika/parser/image/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-mail-module/src/test/java/org/apache/tika/parser/mail/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/test/java/org/apache/tika/parser/miscoffice/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-news-module/src/test/java/org/apache/tika/parser/feed/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/test/java/org/apache/tika/parser/pkg/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/test/java/org/apache/tika/parser/txt/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/test/java/org/apache/tika/parser/warc/XHTMLWellFormednessTest.java
delete mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-xml-module/src/test/java/org/apache/tika/parser/xml/XHTMLWellFormednessTest.java