You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2017/02/23 14:04:57 UTC
tika git commit: TIKA-2276 -- pass through ParseContext to prevent
needless creation of TikaConfig
Repository: tika
Updated Branches:
refs/heads/master 166ebb2b5 -> 1c873399e
TIKA-2276 -- pass through ParseContext to prevent needless creation of TikaConfig
Project: http://git-wip-us.apache.org/repos/asf/tika/repo
Commit: http://git-wip-us.apache.org/repos/asf/tika/commit/1c873399
Tree: http://git-wip-us.apache.org/repos/asf/tika/tree/1c873399
Diff: http://git-wip-us.apache.org/repos/asf/tika/diff/1c873399
Branch: refs/heads/master
Commit: 1c873399ee30af9912a7210e4ced8168f659db04
Parents: 166ebb2
Author: tballison <ta...@mitre.org>
Authored: Thu Feb 23 09:04:51 2017 -0500
Committer: tballison <ta...@mitre.org>
Committed: Thu Feb 23 09:04:51 2017 -0500
----------------------------------------------------------------------
.../src/main/java/org/apache/tika/parser/chm/ChmParser.java | 3 +--
.../org/apache/tika/parser/microsoft/JackcessExtractor.java | 5 +++--
.../org/apache/tika/parser/microsoft/OutlookExtractor.java | 7 ++++---
3 files changed, 8 insertions(+), 7 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/tika/blob/1c873399/tika-parsers/src/main/java/org/apache/tika/parser/chm/ChmParser.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/chm/ChmParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/chm/ChmParser.java
index 3b4e00f..70812f1 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/chm/ChmParser.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/chm/ChmParser.java
@@ -93,10 +93,9 @@ public class ChmParser extends AbstractParser {
Metadata metadata = new Metadata();
HtmlParser htmlParser = new HtmlParser();
ContentHandler handler = new EmbeddedContentHandler(new BodyContentHandler(xhtml));// -1
- ParseContext parser = new ParseContext();
try {
stream = new ByteArrayInputStream(byteObject);
- htmlParser.parse(stream, handler, metadata, parser);
+ htmlParser.parse(stream, handler, metadata, context);
} catch (SAXException e) {
throw new RuntimeException(e);
} catch (IOException e) {
http://git-wip-us.apache.org/repos/asf/tika/blob/1c873399/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/JackcessExtractor.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/JackcessExtractor.java b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/JackcessExtractor.java
index 4442106..c156be0 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/JackcessExtractor.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/JackcessExtractor.java
@@ -69,17 +69,18 @@ class JackcessExtractor extends AbstractPOIFSExtractor {
final static String CURRENCY_FORMAT_KEY = "Format";
final static byte TEXT_FORMAT = 0;
final static byte RICH_TEXT_FORMAT = 1;
- final static ParseContext EMPTY_PARSE_CONTEXT = new ParseContext();
final NumberFormat currencyFormatter;
final DateFormat shortDateTimeFormatter;
final HtmlParser htmlParser = new HtmlParser();
+ final ParseContext parseContext;
protected JackcessExtractor(Metadata metadata, ParseContext context, Locale locale) {
super(context, metadata);
currencyFormatter = NumberFormat.getCurrencyInstance(locale);
shortDateTimeFormatter = DateFormat.getDateInstance(DateFormat.SHORT, locale);
+ this.parseContext = context;
}
public void parse(Database db, XHTMLContentHandler xhtml) throws IOException, SAXException, TikaException {
@@ -205,7 +206,7 @@ class JackcessExtractor extends AbstractPOIFSExtractor {
try {
htmlParser.parse(new ByteArrayInputStream(v.getBytes(UTF_8)),
h,
- m, EMPTY_PARSE_CONTEXT);
+ m, parseContext);
handler.characters(h.toString());
} catch (SAXException e) {
//if something went wrong in htmlparser, just append the characters
http://git-wip-us.apache.org/repos/asf/tika/blob/1c873399/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java
----------------------------------------------------------------------
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java
index 9818d30..14ceee5 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/OutlookExtractor.java
@@ -86,6 +86,7 @@ public class OutlookExtractor extends AbstractPOIFSExtractor {
HtmlEncodingDetector detector = new HtmlEncodingDetector();
private final MAPIMessage msg;
+ private final ParseContext parseContext;
public OutlookExtractor(NPOIFSFileSystem filesystem, ParseContext context) throws TikaException {
this(filesystem.getRoot(), context);
@@ -93,7 +94,7 @@ public class OutlookExtractor extends AbstractPOIFSExtractor {
public OutlookExtractor(DirectoryNode root, ParseContext context) throws TikaException {
super(context);
-
+ this.parseContext = context;
try {
this.msg = new MAPIMessage(root);
} catch (IOException e) {
@@ -227,7 +228,7 @@ public class OutlookExtractor extends AbstractPOIFSExtractor {
htmlParser.parse(
new ByteArrayInputStream(data),
new EmbeddedContentHandler(new BodyContentHandler(xhtml)),
- new Metadata(), new ParseContext()
+ new Metadata(), parseContext
);
doneBody = true;
}
@@ -241,7 +242,7 @@ public class OutlookExtractor extends AbstractPOIFSExtractor {
rtfParser.parse(
new ByteArrayInputStream(rtf.getData()),
new EmbeddedContentHandler(new BodyContentHandler(xhtml)),
- new Metadata(), new ParseContext());
+ new Metadata(), parseContext);
doneBody = true;
}
if (textChunk != null && !doneBody) {