strscan 3.1.2 → 3.1.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 73c77caa81f5b813c59e442c9499b5a7ab4ea7b1150beb9ec2c74e77db6594df
-  data.tar.gz: 06cc976fa2b5da016adee87d62d306c96c64da26ff32cc38c01de113e20403f6
+  metadata.gz: bd2dcf02f3109bb80e827faa389189e0418661d1ad3e2891b3427de98ff91fb2
+  data.tar.gz: cdb3b869dd71609de50939b362ab5d9817222ed01d1c6993ac9a68bab898526b
 SHA512:
-  metadata.gz: 68e02c4724557b03798d0c13761cc84c604278ad482c693208fc448459270faa6653069139757a9b4095c6d0fdecdff75982e8a47172e2602d1173dd6c7bf61c
-  data.tar.gz: f6df1e074a2a6330058d3c8f4b7961a1ab0b3f077860940feadc0515e95deab8fcae3c06fccb4d3482f2127a4479b12e0c1e0482fd638decd047f770331fad47
+  metadata.gz: d4157babafccbe1e81200a97fbc700ea17d4d6ed7f9853d2b3eae8d7ed1a8092d8178819de820c001f922f95ea31283b14e262a60041039323c1c2aa8743fb83
+  data.tar.gz: 53eb84583f0e59b3dd866b1811c8e7481bb0e505bb152fffe157aa08938779cd37e82d8153a82eb57f0f3c858235966a8ee2b5912dfa70576c9624d483816b32

data/.rdoc_options

@@ -1,3 +1,5 @@
 ---
 rdoc_include:
 - doc
+main_page: README.md
+op_dir: html

data/doc/strscan/strscan.md

@@ -37,7 +37,7 @@ Some examples here assume that certain helper methods are defined:
 - `match_values_cleared?(scanner)`:
   Returns whether the scanner's [match values][9] are cleared.
 
-See examples [here][ext/strscan/helper_methods_md.html].
+See examples at [helper methods](helper_methods.md).
 
 ## The `StringScanner` \Object
 
@@ -112,11 +112,11 @@ and a zero-based <i>character position</i>.
 
 Each of these methods explicitly sets positions:
 
-| Method                   | Effect                                                   |
-|--------------------------|----------------------------------------------------------|
-| #reset                   | Sets both positions to zero (begining of stored string). |
-| #terminate               | Sets both positions to the end of the stored string.     |
-| #pos=(new_byte_position) | Sets byte position; adjusts character position.          |
+| Method                   | Effect                                                    |
+|--------------------------|-----------------------------------------------------------|
+| #reset                   | Sets both positions to zero (beginning of stored string). |
+| #terminate               | Sets both positions to the end of the stored string.      |
+| #pos=(new_byte_position) | Sets byte position; adjusts character position.           |
 
 ### Byte Position (Position)
 
@@ -204,7 +204,7 @@ put_situation(scanner)
 
 ## Target Substring
 
-The target substring is the the part of the [stored string][1]
+The target substring is the part of the [stored string][1]
 that extends from the current [byte position][2] to the end of the stored string;
 it is always either:
 
@@ -417,7 +417,7 @@ Each of these methods returns a captured match value:
 | Method          | Return After Match                      | Return After No Match |
 |-----------------|-----------------------------------------|-----------------------|
 | #size           | Count of captured substrings.           | +nil+.                |
-| #[](n)          | <tt>n</tt>th captured substring.        | +nil+.                |
+| #\[\](n)        | <tt>n</tt>th captured substring.        | +nil+.                |
 | #captures       | Array of all captured substrings.       | +nil+.                |
 | #values_at(*n)  | Array of specified captured substrings. | +nil+.                |
 | #named_captures | Hash of named captures.                 | <tt>{}</tt>.          |

data/ext/strscan/extconf.rb

@@ -2,8 +2,9 @@
 require 'mkmf'
 if RUBY_ENGINE == 'ruby'
   $INCFLAGS << " -I$(top_srcdir)" if $extmk
-  have_func("onig_region_memsize", "ruby.h")
-  have_func("rb_reg_onig_match", "ruby.h")
+  have_func("onig_region_memsize(NULL)")
+  have_func("rb_reg_onig_match", "ruby/re.h")
+  have_func("rb_deprecate_constant")
   create_makefile 'strscan'
 else
   File.write('Makefile', dummy_makefile("").join)

data/ext/strscan/strscan.c

@@ -22,7 +22,15 @@ extern size_t onig_region_memsize(const struct re_registers *regs);
 
 #include <stdbool.h>
 
-#define STRSCAN_VERSION "3.1.2"
+#define STRSCAN_VERSION "3.1.7"
+
+
+#ifdef HAVE_RB_DEPRECATE_CONSTANT
+/* In ruby 3.0, defined but exposed in external headers */
+extern void rb_deprecate_constant(VALUE mod, const char *name);
+#else
+# define rb_deprecate_constant(mod, name) ((void)0)
+#endif
 
 /* =======================================================================
                          Data Type Definitions
@@ -30,7 +38,6 @@ extern size_t onig_region_memsize(const struct re_registers *regs);
 
 static VALUE StringScanner;
 static VALUE ScanError;
-static ID id_byteslice;
 
 static int usascii_encindex, utf8_encindex, binary_encindex;
 
@@ -58,8 +65,13 @@ struct strscanner
 };
 
 #define MATCHED_P(s)          ((s)->flags & FLAG_MATCHED)
-#define MATCHED(s)             (s)->flags |= FLAG_MATCHED
-#define CLEAR_MATCH_STATUS(s)  (s)->flags &= ~FLAG_MATCHED
+#define MATCHED(s)            ((s)->flags |= FLAG_MATCHED)
+#define CLEAR_MATCHED(s)      ((s)->flags &= ~FLAG_MATCHED)
+#define CLEAR_NAMED_CAPTURES(s) ((s)->regex = Qnil)
+#define CLEAR_MATCH_STATUS(s) do {\
+    CLEAR_MATCHED(s);\
+    CLEAR_NAMED_CAPTURES(s);\
+} while (0)
 
 #define S_PBEG(s)  (RSTRING_PTR((s)->str))
 #define S_LEN(s)  (RSTRING_LEN((s)->str))
@@ -92,7 +104,6 @@ static VALUE strscan_init_copy _((VALUE vself, VALUE vorig));
 
 static VALUE strscan_s_mustc _((VALUE self));
 static VALUE strscan_terminate _((VALUE self));
-static VALUE strscan_clear _((VALUE self));
 static VALUE strscan_get_string _((VALUE self));
 static VALUE strscan_set_string _((VALUE self, VALUE str));
 static VALUE strscan_concat _((VALUE self, VALUE str));
@@ -114,14 +125,11 @@ static VALUE strscan_search_full _((VALUE self, VALUE re,
 static void adjust_registers_to_matched _((struct strscanner *p));
 static VALUE strscan_getch _((VALUE self));
 static VALUE strscan_get_byte _((VALUE self));
-static VALUE strscan_getbyte _((VALUE self));
 static VALUE strscan_peek _((VALUE self, VALUE len));
-static VALUE strscan_peep _((VALUE self, VALUE len));
 static VALUE strscan_scan_base10_integer _((VALUE self));
 static VALUE strscan_unscan _((VALUE self));
 static VALUE strscan_bol_p _((VALUE self));
 static VALUE strscan_eos_p _((VALUE self));
-static VALUE strscan_empty_p _((VALUE self));
 static VALUE strscan_rest_p _((VALUE self));
 static VALUE strscan_matched_p _((VALUE self));
 static VALUE strscan_matched _((VALUE self));
@@ -204,7 +212,7 @@ strscan_memsize(const void *ptr)
 static const rb_data_type_t strscanner_type = {
     "StringScanner",
     {strscan_mark, strscan_free, strscan_memsize},
-    0, 0, RUBY_TYPED_FREE_IMMEDIATELY
+    0, 0, RUBY_TYPED_FREE_IMMEDIATELY | RUBY_TYPED_WB_PROTECTED
 };
 
 static VALUE
@@ -216,7 +224,6 @@ strscan_s_allocate(VALUE klass)
     CLEAR_MATCH_STATUS(p);
     onig_region_init(&(p->regs));
     p->str = Qnil;
-    p->regex = Qnil;
     return obj;
 }
 
@@ -269,7 +276,7 @@ strscan_initialize(int argc, VALUE *argv, VALUE self)
         p->fixed_anchor_p = false;
     }
     StringValue(str);
-    p->str = str;
+    RB_OBJ_WRITE(self, &p->str, str);
 
     return self;
 }
@@ -299,7 +306,7 @@ strscan_init_copy(VALUE vself, VALUE vorig)
     orig = check_strscan(vorig);
     if (self != orig) {
 	self->flags = orig->flags;
-	self->str = orig->str;
+	RB_OBJ_WRITE(vself, &self->str, orig->str);
 	self->prev = orig->prev;
 	self->curr = orig->curr;
 	if (rb_reg_region_copy(&self->regs, &orig->regs))
@@ -381,21 +388,6 @@ strscan_terminate(VALUE self)
     return self;
 }
 
-/*
- * call-seq:
- *   clear -> self
- *
- * This method is obsolete; use the equivalent method StringScanner#terminate.
- */
-
- /* :nodoc: */
-static VALUE
-strscan_clear(VALUE self)
-{
-    rb_warning("StringScanner#clear is obsolete; use #terminate instead");
-    return strscan_terminate(self);
-}
-
 /*
  * :markup: markdown
  * :include: strscan/link_refs.txt
@@ -463,7 +455,7 @@ strscan_set_string(VALUE self, VALUE str)
     struct strscanner *p = check_strscan(self);
 
     StringValue(str);
-    p->str = str;
+    RB_OBJ_WRITE(self, &p->str, str);
     p->curr = 0;
     CLEAR_MATCH_STATUS(p);
     return str;
@@ -520,7 +512,7 @@ strscan_get_pos(VALUE self)
     struct strscanner *p;
 
     GET_SCANNER(self, p);
-    return INT2FIX(p->curr);
+    return LONG2NUM(p->curr);
 }
 
 /*
@@ -550,7 +542,7 @@ strscan_set_pos(VALUE self, VALUE v)
     long i;
 
     GET_SCANNER(self, p);
-    i = NUM2INT(v);
+    i = NUM2LONG(v);
     if (i < 0) i += S_LEN(p);
     if (i < 0) rb_raise(rb_eRangeError, "index out of range");
     if (i > S_LEN(p)) rb_raise(rb_eRangeError, "index out of range");
@@ -571,19 +563,20 @@ match_target(struct strscanner *p)
 }
 
 static inline void
-set_registers(struct strscanner *p, size_t length)
+set_registers(struct strscanner *p, size_t pos, size_t length)
 {
     const int at = 0;
     OnigRegion *regs = &(p->regs);
     onig_region_clear(regs);
     if (onig_region_set(regs, at, 0, 0)) return;
     if (p->fixed_anchor_p) {
-        regs->beg[at] = p->curr;
-        regs->end[at] = p->curr + length;
+        regs->beg[at] = pos + p->curr;
+        regs->end[at] = pos + p->curr + length;
     }
     else
     {
-        regs->end[at] = length;
+        regs->beg[at] = pos;
+        regs->end[at] = pos + length;
     }
 }
 
@@ -707,7 +700,7 @@ strscan_do_scan(VALUE self, VALUE pattern, int succptr, int getstr, int headonly
 
     if (RB_TYPE_P(pattern, T_REGEXP)) {
         OnigPosition ret;
-        p->regex = pattern;
+        RB_OBJ_WRITE(self, &p->regex, pattern);
         ret = rb_reg_onig_match(p->regex,
                                 p->str,
                                 headonly ? strscan_match : strscan_search,
@@ -731,7 +724,7 @@ strscan_do_scan(VALUE self, VALUE pattern, int succptr, int getstr, int headonly
             if (memcmp(CURPTR(p), RSTRING_PTR(pattern), RSTRING_LEN(pattern)) != 0) {
                 return Qnil;
             }
-            set_registers(p, RSTRING_LEN(pattern));
+            set_registers(p, 0, RSTRING_LEN(pattern));
         }
         else {
             rb_encoding *enc = rb_enc_check(p->str, pattern);
@@ -740,7 +733,7 @@ strscan_do_scan(VALUE self, VALUE pattern, int succptr, int getstr, int headonly
             if (pos == -1) {
                 return Qnil;
             }
-            set_registers(p, RSTRING_LEN(pattern) + pos);
+            set_registers(p, pos, RSTRING_LEN(pattern));
         }
     }
 
@@ -1213,22 +1206,6 @@ strscan_get_byte(VALUE self)
                          adjust_register_position(p, p->regs.end[0]));
 }
 
-/*
- * call-seq:
- *   getbyte
- *
- * Equivalent to #get_byte.
- * This method is obsolete; use #get_byte instead.
- */
-
- /* :nodoc: */
-static VALUE
-strscan_getbyte(VALUE self)
-{
-    rb_warning("StringScanner#getbyte is obsolete; use #get_byte instead");
-    return strscan_get_byte(self);
-}
-
 /*
  * :markup: markdown
  * :include: strscan/link_refs.txt
@@ -1264,22 +1241,6 @@ strscan_peek(VALUE self, VALUE vlen)
     return extract_beg_len(p, p->curr, len);
 }
 
-/*
- * call-seq:
- *   peep
- *
- * Equivalent to #peek.
- * This method is obsolete; use #peek instead.
- */
-
- /* :nodoc: */
-static VALUE
-strscan_peep(VALUE self, VALUE vlen)
-{
-    rb_warning("StringScanner#peep is obsolete; use #peek instead");
-    return strscan_peek(self, vlen);
-}
-
 static VALUE
 strscan_parse_integer(struct strscanner *p, int base, long len)
 {
@@ -1292,6 +1253,10 @@ strscan_parse_integer(struct strscanner *p, int base, long len)
     integer = rb_cstr2inum(buffer, base);
     RB_ALLOCV_END(buffer_v);
     p->curr += len;
+
+    MATCHED(p);
+    adjust_registers_to_matched(p);
+
     return integer;
 }
 
@@ -1313,11 +1278,12 @@ strscan_must_ascii_compat(VALUE str)
     rb_must_asciicompat(str);
 }
 
+/* :nodoc: */
 static VALUE
 strscan_scan_base10_integer(VALUE self)
 {
     char *ptr;
-    long len = 0;
+    long len = 0, remaining_len;
     struct strscanner *p;
 
     GET_SCANNER(self, p);
@@ -1327,7 +1293,7 @@ strscan_scan_base10_integer(VALUE self)
 
     ptr = CURPTR(p);
 
-    long remaining_len = S_RESTLEN(p);
+    remaining_len = S_RESTLEN(p);
 
     if (remaining_len <= 0) {
         return Qnil;
@@ -1341,7 +1307,6 @@ strscan_scan_base10_integer(VALUE self)
         return Qnil;
     }
 
-    MATCHED(p);
     p->prev = p->curr;
 
     while (len < remaining_len && rb_isdigit(ptr[len])) {
@@ -1351,11 +1316,12 @@ strscan_scan_base10_integer(VALUE self)
     return strscan_parse_integer(p, 10, len);
 }
 
+/* :nodoc: */
 static VALUE
 strscan_scan_base16_integer(VALUE self)
 {
     char *ptr;
-    long len = 0;
+    long len = 0, remaining_len;
     struct strscanner *p;
 
     GET_SCANNER(self, p);
@@ -1365,7 +1331,7 @@ strscan_scan_base16_integer(VALUE self)
 
     ptr = CURPTR(p);
 
-    long remaining_len = S_RESTLEN(p);
+    remaining_len = S_RESTLEN(p);
 
     if (remaining_len <= 0) {
         return Qnil;
@@ -1375,7 +1341,7 @@ strscan_scan_base16_integer(VALUE self)
         len++;
     }
 
-    if ((remaining_len >= (len + 2)) && ptr[len] == '0' && ptr[len + 1] == 'x') {
+    if ((remaining_len >= (len + 3)) && ptr[len] == '0' && ptr[len + 1] == 'x' && rb_isxdigit(ptr[len + 2])) {
         len += 2;
     }
 
@@ -1383,7 +1349,6 @@ strscan_scan_base16_integer(VALUE self)
         return Qnil;
     }
 
-    MATCHED(p);
     p->prev = p->curr;
 
     while (len < remaining_len && rb_isxdigit(ptr[len])) {
@@ -1517,28 +1482,11 @@ strscan_eos_p(VALUE self)
     return EOS_P(p) ? Qtrue : Qfalse;
 }
 
-/*
- * call-seq:
- *   empty?
- *
- * Equivalent to #eos?.
- * This method is obsolete, use #eos? instead.
- */
-
- /* :nodoc: */
-static VALUE
-strscan_empty_p(VALUE self)
-{
-    rb_warning("StringScanner#empty? is obsolete; use #eos? instead");
-    return strscan_eos_p(self);
-}
-
 /*
  * call-seq:
  *   rest?
  *
  * Returns true if and only if there is more data in the string.  See #eos?.
- * This method is obsolete; use #eos? instead.
  *
  *   s = StringScanner.new('test string')
  *   # These two are opposites
@@ -1660,19 +1608,17 @@ strscan_matched_size(VALUE self)
 static int
 name_to_backref_number(struct re_registers *regs, VALUE regexp, const char* name, const char* name_end, rb_encoding *enc)
 {
-    int num;
-
-    num = onig_name_to_backref_number(RREGEXP_PTR(regexp),
-	(const unsigned char* )name, (const unsigned char* )name_end, regs);
-    if (num >= 1) {
-	return num;
-    }
-    else {
-	rb_enc_raise(enc, rb_eIndexError, "undefined group name reference: %.*s",
-					  rb_long2int(name_end - name), name);
+    if (RTEST(regexp)) {
+        int num = onig_name_to_backref_number(RREGEXP_PTR(regexp),
+                                              (const unsigned char* )name,
+                                              (const unsigned char* )name_end,
+                                              regs);
+        if (num >= 1) {
+	    return num;
+        }
     }
-
-    UNREACHABLE;
+    rb_enc_raise(enc, rb_eIndexError, "undefined group name reference: %.*s",
+                 rb_long2int(name_end - name), name);
 }
 
 /*
@@ -1761,7 +1707,6 @@ strscan_aref(VALUE self, VALUE idx)
             idx = rb_sym2str(idx);
             /* fall through */
         case T_STRING:
-            if (!RTEST(p->regex)) return Qnil;
             RSTRING_GETMEM(idx, name, i);
             i = name_to_backref_number(&(p->regs), p->regex, name, name + i, rb_enc_get(idx));
             break;
@@ -2049,22 +1994,6 @@ strscan_rest_size(VALUE self)
     return INT2FIX(i);
 }
 
-/*
- * call-seq:
- *   restsize
- *
- * <tt>s.restsize</tt> is equivalent to <tt>s.rest_size</tt>.
- * This method is obsolete; use #rest_size instead.
- */
-
- /* :nodoc: */
-static VALUE
-strscan_restsize(VALUE self)
-{
-    rb_warning("StringScanner#restsize is obsolete; use #rest_size instead");
-    return strscan_rest_size(self);
-}
-
 #define INSPECT_LENGTH 5
 
 /*
@@ -2207,7 +2136,10 @@ named_captures_iter(const OnigUChar *name,
     VALUE value = RUBY_Qnil;
     int i;
     for (i = 0; i < back_num; i++) {
-        value = strscan_aref(data->self, INT2NUM(back_refs[i]));
+        VALUE v = strscan_aref(data->self, INT2NUM(back_refs[i]));
+        if (!RB_NIL_P(v)) {
+            value = v;
+        }
     }
     rb_hash_aset(data->captures, key, value);
     return 0;
@@ -2260,6 +2192,13 @@ strscan_named_captures(VALUE self)
                               Ruby Interface
    ======================================================================= */
 
+/*
+ * Document-class: StringScanner::Error
+ *
+ * The error class for StringScanner.
+ * See StringScanner#unscan.
+ */
+
 /*
  * Document-class: StringScanner
  *
@@ -2280,8 +2219,6 @@ Init_strscan(void)
     ID id_scanerr = rb_intern("ScanError");
     VALUE tmp;
 
-    id_byteslice = rb_intern("byteslice");
-
     usascii_encindex = rb_usascii_encindex();
     utf8_encindex = rb_utf8_encindex();
     binary_encindex = rb_ascii8bit_encindex();
@@ -2290,6 +2227,7 @@ Init_strscan(void)
     ScanError = rb_define_class_under(StringScanner, "Error", rb_eStandardError);
     if (!rb_const_defined(rb_cObject, id_scanerr)) {
 	rb_const_set(rb_cObject, id_scanerr, ScanError);
+	rb_deprecate_constant(rb_cObject, "ScanError");
     }
     tmp = rb_str_new2(STRSCAN_VERSION);
     rb_obj_freeze(tmp);
@@ -2297,6 +2235,7 @@ Init_strscan(void)
     tmp = rb_str_new2("$Id$");
     rb_obj_freeze(tmp);
     rb_const_set(StringScanner, rb_intern("Id"), tmp);
+    rb_deprecate_constant(StringScanner, "Id");
 
     rb_define_alloc_func(StringScanner, strscan_s_allocate);
     rb_define_private_method(StringScanner, "initialize", strscan_initialize, -1);
@@ -2304,7 +2243,6 @@ Init_strscan(void)
     rb_define_singleton_method(StringScanner, "must_C_version", strscan_s_mustc, 0);
     rb_define_method(StringScanner, "reset",       strscan_reset,       0);
     rb_define_method(StringScanner, "terminate",   strscan_terminate,   0);
-    rb_define_method(StringScanner, "clear",       strscan_clear,       0);
     rb_define_method(StringScanner, "string",      strscan_get_string,  0);
     rb_define_method(StringScanner, "string=",     strscan_set_string,  1);
     rb_define_method(StringScanner, "concat",      strscan_concat,      1);
@@ -2329,11 +2267,9 @@ Init_strscan(void)
 
     rb_define_method(StringScanner, "getch",       strscan_getch,       0);
     rb_define_method(StringScanner, "get_byte",    strscan_get_byte,    0);
-    rb_define_method(StringScanner, "getbyte",     strscan_getbyte,     0);
     rb_define_method(StringScanner, "scan_byte",   strscan_scan_byte,   0);
     rb_define_method(StringScanner, "peek",        strscan_peek,        1);
     rb_define_method(StringScanner, "peek_byte",   strscan_peek_byte,   0);
-    rb_define_method(StringScanner, "peep",        strscan_peep,        1);
 
     rb_define_private_method(StringScanner, "scan_base10_integer", strscan_scan_base10_integer, 0);
     rb_define_private_method(StringScanner, "scan_base16_integer", strscan_scan_base16_integer, 0);
@@ -2343,7 +2279,6 @@ Init_strscan(void)
     rb_define_method(StringScanner, "beginning_of_line?", strscan_bol_p, 0);
     rb_alias(StringScanner, rb_intern("bol?"), rb_intern("beginning_of_line?"));
     rb_define_method(StringScanner, "eos?",        strscan_eos_p,       0);
-    rb_define_method(StringScanner, "empty?",      strscan_empty_p,     0);
     rb_define_method(StringScanner, "rest?",       strscan_rest_p,      0);
 
     rb_define_method(StringScanner, "matched?",    strscan_matched_p,   0);
@@ -2358,7 +2293,6 @@ Init_strscan(void)
 
     rb_define_method(StringScanner, "rest",        strscan_rest,        0);
     rb_define_method(StringScanner, "rest_size",   strscan_rest_size,   0);
-    rb_define_method(StringScanner, "restsize",    strscan_restsize,    0);
 
     rb_define_method(StringScanner, "inspect",     strscan_inspect,     0);
 

metadata

@@ -1,16 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: strscan
 version: !ruby/object:Gem::Version
-  version: 3.1.2
+  version: 3.1.7
 platform: ruby
 authors:
 - Minero Aoki
 - Sutou Kouhei
 - Charles Oliver Nutter
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-12-15 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies: []
 description: Provides lexical scanning operations on a String.
 email:
@@ -60,7 +59,6 @@ licenses:
 - Ruby
 - BSD-2-Clause
 metadata: {}
-post_install_message:
 rdoc_options:
 - "-idoc"
 require_paths:
@@ -76,8 +74,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.22
-signing_key:
+rubygems_version: 4.0.3
 specification_version: 4
 summary: Provides lexical scanning operations on a String.
 test_files: []