utf8 0.1.3 → 0.1.4

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.
@@ -3,6 +3,8 @@
3
3
 
4
4
  extern VALUE intern_as_utf8;
5
5
 
6
+ #define REPLACEMENT_CHAR '?'
7
+
6
8
  /*
7
9
  * Document-class: String::UTF-8
8
10
  */
@@ -112,7 +114,7 @@ static VALUE rb_cString_UTF8_valid(int argc, VALUE *argv, VALUE self) {
112
114
  }
113
115
 
114
116
  for(; i<len; i+=lastCharLen) {
115
- lastCharLen = utf8CharLen(str, len);
117
+ lastCharLen = utf8CharLen(str+i, len);
116
118
  if (lastCharLen < 0) {
117
119
  return Qfalse;
118
120
  }
@@ -327,6 +329,42 @@ static VALUE rb_cString_UTF8_slice(int argc, VALUE *argv, VALUE self) {
327
329
  }
328
330
  }
329
331
 
332
+ /*
333
+ * call-seq: clean
334
+ *
335
+ * Iterates over the string, replacing invalid UTF-8 characters with '?'
336
+ *
337
+ * Returns: a new String
338
+ */
339
+ static VALUE rb_cString_UTF8_clean(VALUE self) {
340
+ unsigned char *str;
341
+ unsigned char *out;
342
+ unsigned char replace;
343
+ size_t len;
344
+ int8_t curCharLen;
345
+ size_t i;
346
+ VALUE rb_out;
347
+
348
+ str = (unsigned char *)RSTRING_PTR(self);
349
+ len = RSTRING_LEN(self);
350
+ replace = REPLACEMENT_CHAR;
351
+ out = xmalloc(len);
352
+
353
+ for(i=0; i<len; i++) {
354
+ curCharLen = utf8CharLen(str+i, len);
355
+ if (curCharLen < 0) {
356
+ *(out+i) = replace;
357
+ } else {
358
+ *(out+i) = *(str+i);
359
+ }
360
+ }
361
+
362
+ rb_out = rb_str_new((const char*)out, len);
363
+ AS_UTF8(rb_out);
364
+
365
+ return rb_out;
366
+ }
367
+
330
368
  void init_String_UTF8() {
331
369
  VALUE rb_cString_UTF8 = rb_define_class_under(rb_cString, "UTF8", rb_cString);
332
370
 
@@ -335,4 +373,5 @@ void init_String_UTF8() {
335
373
  rb_define_method(rb_cString_UTF8, "[]", rb_cString_UTF8_slice, -1);
336
374
  rb_define_method(rb_cString_UTF8, "each_codepoint", rb_cString_UTF8_each_codepoint, -1);
337
375
  rb_define_method(rb_cString_UTF8, "valid?", rb_cString_UTF8_valid, -1);
376
+ rb_define_method(rb_cString_UTF8, "clean", rb_cString_UTF8_clean, 0);
338
377
  }
data/lib/utf8/version.rb CHANGED
@@ -1,5 +1,5 @@
1
1
  class String
2
2
  class UTF8 < ::String
3
- VERSION = "0.1.3"
3
+ VERSION = "0.1.4"
4
4
  end
5
5
  end
data/spec/string_spec.rb CHANGED
@@ -50,6 +50,12 @@ describe String::UTF8 do
50
50
  @utf8.chars.to_a[0].class.should eql(String::UTF8)
51
51
  end
52
52
 
53
+ it "clean should replace invalid utf8 chars with '?'" do
54
+ orig = "provided by Cristian Rodr\355guez."
55
+ clean = "provided by Cristian Rodr?guez."
56
+ orig.as_utf8.clean.should eql(clean)
57
+ end
58
+
53
59
  context "#length and #size" do
54
60
  it "should be utf8-aware" do
55
61
  @utf8.length.should eql(@utf8_len)
@@ -185,6 +191,8 @@ describe String::UTF8 do
185
191
 
186
192
  utf8.valid?.should be_false
187
193
  @utf8.valid?.should be_true
194
+
195
+ "provided by Cristian Rodr\355guez.".as_utf8.should_not be_valid
188
196
  end
189
197
 
190
198
  it "should test validity using a maximum codepoint" do
metadata CHANGED
@@ -1,13 +1,13 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: utf8
3
3
  version: !ruby/object:Gem::Version
4
- hash: 29
4
+ hash: 19
5
5
  prerelease:
6
6
  segments:
7
7
  - 0
8
8
  - 1
9
- - 3
10
- version: 0.1.3
9
+ - 4
10
+ version: 0.1.4
11
11
  platform: ruby
12
12
  authors:
13
13
  - Brian Lopez
@@ -15,7 +15,7 @@ autorequire:
15
15
  bindir: bin
16
16
  cert_chain: []
17
17
 
18
- date: 2011-06-02 00:00:00 -07:00
18
+ date: 2011-07-21 00:00:00 -07:00
19
19
  default_executable:
20
20
  dependencies:
21
21
  - !ruby/object:Gem::Dependency
@@ -129,7 +129,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
129
129
  requirements: []
130
130
 
131
131
  rubyforge_project:
132
- rubygems_version: 1.6.2
132
+ rubygems_version: 1.3.10
133
133
  signing_key:
134
134
  specification_version: 3
135
135
  summary: A lightweight UTF8-aware String class meant for use with Ruby 1.8