Skip to content

option for turning off/on substrings indexing #6

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Kenneth-KT wants to merge 1 commit into
base: master
Choose a base branch
from
Open

option for turning off/on substrings indexing #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions Classes/MHTextIndex.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@ typedef struct {
@property NSSortOptions sortOptions;
@property NSUInteger minimalTokenLength;
@property BOOL skipStopWords;
@property BOOL indexAllSubstrings;
@property BOOL discardDuplicateTokens;

@property (strong, readonly) NSString * path;
Expand Down
12 changes: 9 additions & 3 deletions Classes/MHTextIndex.m
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,7 +164,7 @@ void removeIndexForStringInObject(NSData *ident, NSUInteger stringIdx, LDBWriteb
}];
}
void indexWordInObjectTextFragment(NSData *ident, NSStringEncoding encoding, bloom_filter_s *bloomFilter,
NSUInteger minimalTokenLength, BOOL skipStopWords,
NSUInteger minimalTokenLength, BOOL skipStopWords, BOOL indexAllSubstrings,
NSString *wordSubstring, NSRange wordSubstringRange, NSUInteger stringIdx,
LDBWritebatch *wb) {

Expand Down Expand Up @@ -265,6 +265,9 @@ void indexWordInObjectTextFragment(NSData *ident, NSStringEncoding encoding, blo

// ... and append the key bytes, without the leading type 0
[keys appendBytes:key length:(NSUInteger)keyLength];

// run only the first loop that indexes the whole word if not indexing all substrings
if (!indexAllSubstrings) break;
}

// Finally, for each indexed word, we need to insert a reversed index entry for bookkeeping
Expand Down Expand Up @@ -314,6 +317,7 @@ - (instancetype)initWithName:(NSString *)name path:(NSString *)path options:(Lev
_indexingQueue.maxConcurrentOperationCount = 10;

_minimalTokenLength = 2;
_indexAllSubstrings = YES;
_skipStopWords = YES;
_discardDuplicateTokens = NO;

Expand Down Expand Up @@ -443,7 +447,8 @@ - (NSOperation *)indexObject:(id)object {
usingBlock:^(NSString *substring, NSRange substringRange, NSRange enclosingRange, BOOL *stop) {
indexWordInObjectTextFragment(ident, encoding, bloomFilter,
_sself->_minimalTokenLength, _sself->_skipStopWords,
substring, substringRange, idx, wb);
_sself->_indexAllSubstrings, substring,
substringRange, idx, wb);
}];

if (_sself->_discardDuplicateTokens)
Expand Down Expand Up @@ -519,7 +524,8 @@ - (NSOperation *)updateIndexForObject:(id)object {
usingBlock:^(NSString *substring, NSRange substringRange, NSRange enclosingRange, BOOL *stop) {
indexWordInObjectTextFragment(ident, encoding, bloomFilter,
_sself->_minimalTokenLength, _sself->_skipStopWords,
substring, substringRange, idx, wb);
_sself->_indexAllSubstrings, substring,
substringRange, idx, wb);
}];

if (_sself->_discardDuplicateTokens)
Expand Down