chinwag 0.1.5 → 1.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/Rakefile +1 -1
- data/ext/chinwag/chinwag.c +46 -41
- data/ext/chinwag/chinwag.h +20 -12
- data/ext/chinwag/config.c +6 -6
- data/ext/chinwag/dict.c +211 -107
- data/ext/chinwag/dict.h +93 -41
- data/ext/chinwag/latin.h +2 -2
- data/ext/chinwag/rb_chinwag_ext.c +255 -167
- data/ext/chinwag/seuss.h +2 -2
- data/ext/chinwag/tokenize.c +7 -5
- data/ext/chinwag/tokenize.h +5 -2
- metadata +2 -2
data/ext/chinwag/seuss.h
CHANGED
data/ext/chinwag/tokenize.c
CHANGED
|
@@ -1,6 +1,7 @@
|
|
|
1
1
|
#include "tokenize.h"
|
|
2
2
|
|
|
3
|
-
U32 stringify_file
|
|
3
|
+
U32 stringify_file
|
|
4
|
+
(char** buffer, FILE* fp)
|
|
4
5
|
{
|
|
5
6
|
// setup
|
|
6
7
|
U64 sz = 0;
|
|
@@ -22,11 +23,12 @@ U32 stringify_file(char** buffer, FILE* fp)
|
|
|
22
23
|
return sz;
|
|
23
24
|
}
|
|
24
25
|
|
|
25
|
-
|
|
26
|
+
cwdict_t tokenize
|
|
27
|
+
(const char* const buffer, const char* delimiters)
|
|
26
28
|
{
|
|
27
29
|
char* tok;
|
|
28
30
|
char* mutable_buffer = (char*)malloc(strlen(buffer) + 1 * sizeof(char));
|
|
29
|
-
|
|
31
|
+
cwdict_t dict = cwdict_open();
|
|
30
32
|
|
|
31
33
|
// get mutable copy of buffer; a bit slower, but allows for const-ness
|
|
32
34
|
strcpy(mutable_buffer, buffer);
|
|
@@ -37,7 +39,7 @@ dict_t tokenize(const char* const buffer, const char* delimiters)
|
|
|
37
39
|
while(tok != NULL)
|
|
38
40
|
{
|
|
39
41
|
// add tok to dict
|
|
40
|
-
dict =
|
|
42
|
+
dict = cwdict_place_word_strict(dict, tok);
|
|
41
43
|
|
|
42
44
|
// get new tok (if any)
|
|
43
45
|
tok = strtok(NULL, delimiters);
|
|
@@ -47,7 +49,7 @@ dict_t tokenize(const char* const buffer, const char* delimiters)
|
|
|
47
49
|
free(mutable_buffer);
|
|
48
50
|
|
|
49
51
|
// clean up dict
|
|
50
|
-
dict =
|
|
52
|
+
dict = cwdict_prune(dict, true);
|
|
51
53
|
|
|
52
54
|
return dict;
|
|
53
55
|
}
|
data/ext/chinwag/tokenize.h
CHANGED
|
@@ -3,7 +3,10 @@
|
|
|
3
3
|
|
|
4
4
|
#include "chinwag.h"
|
|
5
5
|
|
|
6
|
-
U32 stringify_file
|
|
7
|
-
|
|
6
|
+
U32 stringify_file
|
|
7
|
+
(char** buffer, FILE* fp);
|
|
8
|
+
|
|
9
|
+
cwdict_t tokenize
|
|
10
|
+
(const char* const buffer, const char* delimiters);
|
|
8
11
|
|
|
9
12
|
#endif
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: chinwag
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version:
|
|
4
|
+
version: 1.2.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Chris Calo
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date:
|
|
11
|
+
date: 2015-01-04 00:00:00.000000000 Z
|
|
12
12
|
dependencies: []
|
|
13
13
|
description: A text-synthesis library, for use in layout testing (and more). It houses
|
|
14
14
|
flexible methods for generation, and a dictionary class (CWDict) allowing adequate
|