This is an automated email from the ASF dual-hosted git repository.
mibo pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/olingo-odata4.git
The following commit(s) were added to refs/heads/master by this push:
new 683e471dc [OLINGO-1571] Fixed special chars for search
683e471dc is described below
commit 683e471dc2f06d3f2ca06a7a9c95e1480532fe98
Author: mibo <[email protected]>
AuthorDate: Mon Aug 8 20:06:20 2022 +0200
[OLINGO-1571] Fixed special chars for search
---
.../core/uri/parser/search/SearchTokenizer.java | 87 +++-------------------
.../uri/parser/search/SearchTokenizerTest.java | 13 +++-
2 files changed, 20 insertions(+), 80 deletions(-)
diff --git
a/lib/server-core/src/main/java/org/apache/olingo/server/core/uri/parser/search/SearchTokenizer.java
b/lib/server-core/src/main/java/org/apache/olingo/server/core/uri/parser/search/SearchTokenizer.java
index 6f7e01e70..853537d3b 100644
---
a/lib/server-core/src/main/java/org/apache/olingo/server/core/uri/parser/search/SearchTokenizer.java
+++
b/lib/server-core/src/main/java/org/apache/olingo/server/core/uri/parser/search/SearchTokenizer.java
@@ -124,83 +124,17 @@ public class SearchTokenizer {
|| isOtherDelimsForWord(character);
}
- /**
- * <code>
- * <b>searchPhrase</b> = quotation-mark 1*qchar-no-AMP-DQUOTE
quotation-mark
- * <br/><br/>
- * <b>qchar-no-AMP-DQUOTE</b> = qchar-unescaped / escape ( escape /
quotation-mark )
- * <br/><br/>
- * <b>qchar-unescaped</b> = unreserved / pct-encoded-unescaped /
other-delims /
- * ":" / "@" / "/" / "?" / "$" / "'" / "="
- * <br/><br/>
- * <b>unreserved</b> = ALPHA / DIGIT / "-" / "." / "_" / "~"
- * <br/><br/>
- * <b>escape</b> = "\" / "%5C" ; reverse solidus U+005C
- * <br/><br/>
- * <b>pct-encoded-unescaped</b> = "%" ( "0" / "1" / "3" / "4" / "6" / "7"
/ "8" / "9" / A-to-F ) HEXDIG
- * / "%" "2" ( "0" / "1" / "3" / "4" / "5" / "6" / "7" / "8" / "9" /
A-to-F )
- * / "%" "5" ( DIGIT / "A" / "B" / "D" / "E" / "F" )
- * <br/><br/>
- * <b>other-delims</b> = "!" / "(" / ")" / "*" / "+" / "," / ";"
- * <br/><br/>
- * <b>quotation-mark</b> = DQUOTE / "%22"
- * <br/><br/>
- * <b>ALPHA</b> = %x41-5A / %x61-7A
- * <br/>
- * <b>DIGIT</b> = %x30-39
- * <br/>
- * <b>DQUOTE</b> = %x22
- * </code>
- *
- * Checks if given <code>character</code> is allowed for a search phrase.
- * <b>ATTENTION:</b> Escaping and percent encoding is not be validated
here (and can not be validated on
- * a single character).<br/>
- * Hence for the {@link #PHRASE_ESCAPE_CHAR} and the {@link
#QUOTATION_MARK} characters this method will
- * return <code>FALSE</code>.<br/>
- * <b>Furthermore</b> percent encoded characters are also not validated
(and can not be validated on
- * a single character).<br/>
- * Hence for the <code>%</code> character this method assumeS that it was
percent encoded and is now decoded
- * and will return <code>TRUE</code>.<br/>
+ /**
+ * The check for allowed characters in a <code>SearchPhrase</code> assumes
that
+ * the whole phrase is already percent decoded.
+ * Hence, all characters are allowed besides the double quote
(<code>"</code>).
*
* @param character which is checked
* @return true if character is allowed for a phrase
*/
static boolean isAllowedPhrase(final char character) {
- // the '%' is allowed because it is assumed that it was percent encoded
and is now decoded
- return isQCharUnescaped(character)
- || character == '%'
- || Character.isUnicodeIdentifierStart(character);
- }
-
- /**
- * qchar-unescaped = unreserved / pct-encoded-unescaped / other-delims /
":" / "@" / "/" / "?" / "$" / "'" / "="
- * @param character which is checked
- * @return true if character is allowed
- */
- private static boolean isQCharUnescaped(final char character) {
- return isUnreserved(character)
- || isOtherDelims(character)
- || character == ':'
- || character == '@'
- || character == '/'
- || character == '$'
- || character == '\''
- || character == '=';
- }
-
- /**
- * other-delims = "!" / "(" / ")" / "*" / "+" / "," / ";"
- * @param character which is checked
- * @return true if character is allowed
- */
- private static boolean isOtherDelims(final char character) {
- return character == '!'
- || character == '('
- || character == ')'
- || character == '*'
- || character == '+'
- || character == ','
- || character == ';';
+ return Character.isUnicodeIdentifierStart(character)
+ || character != '"';
}
/**
@@ -212,7 +146,6 @@ public class SearchTokenizer {
return character == '!'
|| character == '*'
|| character == '+'
- || character == ','
|| character == ':'
|| character == '@'
|| character == '/'
@@ -234,7 +167,7 @@ public class SearchTokenizer {
|| character == '<'
|| character == '`';
}
-
+
/**
* unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
* @param character which is checked
@@ -355,11 +288,11 @@ public class SearchTokenizer {
}
/**
- *
- * As per the updated abnf
+ *
+ * As per the updated abnf
*
https://github.com/oasis-tcs/odata-abnf/blob/master/abnf/odata-abnf-construction-rules.txt#L332-L356.
* searchWord = 1*( ALPHA / DIGIT / COMMA / "." / "-" / pct-encoded )
- * This includes Unicode characters of categories
+ * This includes Unicode characters of categories
* L or N using UTF-8 and percent-encoding.
*/
private class SearchWordState extends LiteralState {
diff --git
a/lib/server-core/src/test/java/org/apache/olingo/server/core/uri/parser/search/SearchTokenizerTest.java
b/lib/server-core/src/test/java/org/apache/olingo/server/core/uri/parser/search/SearchTokenizerTest.java
index d8c6a7cc7..cea6d3012 100644
---
a/lib/server-core/src/test/java/org/apache/olingo/server/core/uri/parser/search/SearchTokenizerTest.java
+++
b/lib/server-core/src/test/java/org/apache/olingo/server/core/uri/parser/search/SearchTokenizerTest.java
@@ -6,9 +6,9 @@
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
- *
+ *
* http://www.apache.org/licenses/LICENSE-2.0
- *
+ *
* Unless required by applicable law or agreed to in writing,
* software distributed under the License is distributed on an
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
@@ -107,6 +107,13 @@ public class SearchTokenizerTest {
assertQuery("abc or \"xyz\"").resultsIn(WORD, WORD, PHRASE);
}
+ @Test
+ public void parsePhrase_decoded() throws Exception {
+ assertQuery("\"a & b\"").resultsIn(PHRASE);
+ assertQuery("\" ! # $ % & ' ( ) * + , / : ; = ? @ [ ]
\"").resultsIn(PHRASE);
+ assertQuery("\" - . < > ^ _ ` { | } ~ \"").resultsIn(PHRASE);
+ }
+
@Test
public void parseNot() throws Exception {
assertQuery("NOT").resultsIn(NOT);
@@ -401,4 +408,4 @@ public class SearchTokenizerTest {
}
}
}
-}
\ No newline at end of file
+}
