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 2017/07/14 13:13:44 UTC
[tika] branch master updated (12cce58 -> f3acaed)
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/tika.git.
from 12cce58 Merge branch 'onealj-patch2'
add 9687f08 SUPPORTED_TYPES is an immutable singleton set
new 13ebacf Fix conflicts. This closes #193
new f3acaed Fix conflicts. This closes #193. Thank you, Javen!
The 2 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
Summary of changes:
.../main/java/org/apache/tika/parser/microsoft/xml/WordMLParser.java | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
--
To stop receiving notification emails like this one, please contact
['"commits@tika.apache.org" <co...@tika.apache.org>'].
[tika] 01/02: Fix conflicts. This closes #193
Posted by ta...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/tika.git
commit 13ebacfc3ee564b60bef50b20312a866dc18937b
Merge: 12cce58 9687f08
Author: tballison <ta...@mitre.org>
AuthorDate: Fri Jul 14 09:11:04 2017 -0400
Fix conflicts. This closes #193
.../java/org/apache/tika/parser/microsoft/xml/WordMLParser.java | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --cc tika-parsers/src/main/java/org/apache/tika/parser/microsoft/xml/WordMLParser.java
index c22ecd2,ce4daa6..afa1e8e
--- a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/xml/WordMLParser.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/xml/WordMLParser.java
@@@ -18,10 -18,7 +18,9 @@@ package org.apache.tika.parser.microsof
import javax.xml.namespace.QName;
import java.io.IOException;
+import java.util.Arrays;
import java.util.Collections;
- import java.util.HashMap;
+import java.util.HashSet;
import java.util.Locale;
import java.util.Map;
import java.util.Set;
@@@ -52,30 -50,30 +51,29 @@@ public class WordMLParser extends Abstr
//map between wordml and xhtml entities
- private final static Map<String, String> WORDML_TO_XHTML =
- new ConcurrentHashMap<>();
+ private static final Map<String, String> WORDML_TO_XHTML;
+ static {
+ Map<String, String> m = new HashMap<>();
+ m.put(P, P);
+ m.put("tbl", TABLE);
+ m.put(TR, TR);
+ m.put("tc", TD);//not a typo -- table cell -> tc
+ WORDML_TO_XHTML = Collections.unmodifiableMap(m);
+ }
//ignore all characters within these elements
- private final static Set<QName> IGNORE_CHARACTERS =
- Collections.newSetFromMap(new ConcurrentHashMap<QName, Boolean>());
+ private static final Set<QName> IGNORE_CHARACTERS =
+ Collections.unmodifiableSet(new HashSet<>(Arrays.asList(
+ new QName(WORD_ML_URL, HLINK),
+ new QName(WORD_ML_URL, PICT),
+ new QName(WORD_ML_URL, BIN_DATA),
+ new QName(MS_OFFICE_PROPERTIES_URN, DOCUMENT_PROPERTIES))));
-
++
private static final MediaType MEDIA_TYPE = MediaType.application("vnd.ms-wordml");
private static final Set<MediaType> SUPPORTED_TYPES =
- Collections.unmodifiableSet(new HashSet<>(Arrays.asList(
- MEDIA_TYPE)));
+ Collections.singleton(MEDIA_TYPE);
- static {
- WORDML_TO_XHTML.put(P, P);
- WORDML_TO_XHTML.put("tbl", TABLE);
- WORDML_TO_XHTML.put(TR, TR);
- WORDML_TO_XHTML.put("tc", TD);//not a typo -- table cell -> tc
-
- IGNORE_CHARACTERS.add(new QName(WORD_ML_URL, HLINK));
- IGNORE_CHARACTERS.add(new QName(WORD_ML_URL, PICT));
- IGNORE_CHARACTERS.add(new QName(WORD_ML_URL, BIN_DATA));
- IGNORE_CHARACTERS.add(new QName(MS_OFFICE_PROPERTIES_URN,
- DOCUMENT_PROPERTIES));
- }
-
@Override
public Set<MediaType> getSupportedTypes(ParseContext context) {
return SUPPORTED_TYPES;
--
To stop receiving notification emails like this one, please contact
"commits@tika.apache.org" <co...@tika.apache.org>.
[tika] 02/02: Fix conflicts. This closes #193. Thank you, Javen!
Posted by ta...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/tika.git
commit f3acaed38361c35d940ce2742a18b1eec9d7c4f2
Author: tballison <ta...@mitre.org>
AuthorDate: Fri Jul 14 09:13:34 2017 -0400
Fix conflicts. This closes #193. Thank you, Javen!
---
.../src/main/java/org/apache/tika/parser/microsoft/xml/WordMLParser.java | 1 +
1 file changed, 1 insertion(+)
diff --git a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/xml/WordMLParser.java b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/xml/WordMLParser.java
index afa1e8e..3c87c81 100644
--- a/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/xml/WordMLParser.java
+++ b/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/xml/WordMLParser.java
@@ -20,6 +20,7 @@ import javax.xml.namespace.QName;
import java.io.IOException;
import java.util.Arrays;
import java.util.Collections;
+import java.util.HashMap;
import java.util.HashSet;
import java.util.Locale;
import java.util.Map;
--
To stop receiving notification emails like this one, please contact
"commits@tika.apache.org" <co...@tika.apache.org>.