mstoeck3/autopsy-flatpak
1
0
Fork 0
mirror of https://github.com/overcuriousity/autopsy-flatpak.git synced 2025-07-19 11:07:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

Changed set of boundary characters into a character class expression which eliminates the need for the 'or' (|) character.

Browse Source
This commit is contained in:
esaunders 2017-01-10 11:04:50 -05:00
parent acf05a45e8
commit 0aa5d0f63b
1 changed files with 13 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
KeywordSearch/src/org/sleuthkit/autopsy/keywordsearch/RegexQuery.java
View File

@ -84,7 +84,7 @@ final class RegexQuery implements KeywordSearchQuery {
// keyword hit. We use these characters to try to turn the hit into a // keyword hit. We use these characters to try to turn the hit into a
// token that can be more readily matched when it comes to highlighting // token that can be more readily matched when it comes to highlighting
// against the Schema.TEXT field later. // against the Schema.TEXT field later.
private static final String BOUNDARY_CHARS = "(\\s|\\[|\\]|\\(|\\)|\\,|\\!|\\?|\\:|;|=|\\<|\\>|\\^|\\{|\\})"; //NON-NLS private static final String BOUNDARY_CHARS = "[\\s\\[\\]\\(\\)\\,\\\"\\\'\\!\\?\\.\\/\\:\\;\\=\\<\\>\\^\\{\\}]"; //NON-NLS
private boolean queryStringContainsWildcardPrefix = false; private boolean queryStringContainsWildcardPrefix = false;
private boolean queryStringContainsWildcardSuffix = false; private boolean queryStringContainsWildcardSuffix = false;
@ -238,12 +238,22 @@ final class RegexQuery implements KeywordSearchQuery {
+ (queryStringContainsWildcardSuffix ? "" : BOUNDARY_CHARS); //NON-NLS + (queryStringContainsWildcardSuffix ? "" : BOUNDARY_CHARS); //NON-NLS
Matcher hitMatcher = Pattern.compile(keywordTokenRegex).matcher(content); Matcher hitMatcher = Pattern.compile(keywordTokenRegex).matcher(content);
int offset = 0;
while (hitMatcher.find()) { while (hitMatcher.find(offset)) {
StringBuilder snippet = new StringBuilder(); StringBuilder snippet = new StringBuilder();
String hit = hitMatcher.group(); String hit = hitMatcher.group();
// Remove leading and trailing boundary characters. // Back the matcher offset up by 1 character as it will have eaten
// a single space/newline/other boundary character at the end of the hit.
// This was causing us to miss hits that appeared consecutively in the
// input where they were separated by a single boundary character.
offset = hitMatcher.end() - 1;
// Remove leading and trailing whitespace.
hit = hit.trim();
// Remove any remaining leading and trailing boundary characters.
if (!queryStringContainsWildcardPrefix) { if (!queryStringContainsWildcardPrefix) {
hit = hit.replaceAll("^" + BOUNDARY_CHARS, ""); //NON-NLS hit = hit.replaceAll("^" + BOUNDARY_CHARS, ""); //NON-NLS
} }