gosu 1.4.1 → 1.4.3

data/dependencies/utf8proc/utf8proc.c

@@ -1,6 +1,6 @@
 /* -*- mode: c; c-basic-offset: 2; tab-width: 2; indent-tabs-mode: nil -*- */
 /*
- *  Copyright (c) 2018 Steven G. Johnson, Jiahao Chen, Peter Colberg, Tony Kelman, Scott P. Jones, and other contributors.
+ *  Copyright (c) 2014-2021 Steven G. Johnson, Jiahao Chen, Peter Colberg, Tony Kelman, Scott P. Jones, and other contributors.
  *  Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
  *
  *  Permission is hereby granted, free of charge, to any person obtaining a
@@ -27,7 +27,7 @@
  *  Unicode data files.
  *
  *  The original data files are available at
- *  http://www.unicode.org/Public/UNIDATA/
+ *  https://www.unicode.org/Public/UNIDATA/
  *
  *  Please notice the copyright statement in the file "utf8proc_data.c".
  */
@@ -101,7 +101,7 @@ UTF8PROC_DLLEXPORT const char *utf8proc_version(void) {
 }
 
 UTF8PROC_DLLEXPORT const char *utf8proc_unicode_version(void) {
-  return "12.1.0";
+  return "14.0.0";
 }
 
 UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode) {
@@ -125,7 +125,7 @@ UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode) {
 UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_iterate(
   const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_int32_t *dst
 ) {
-  utf8proc_uint32_t uc;
+  utf8proc_int32_t uc;
   const utf8proc_uint8_t *end;
 
   *dst = -1;
@@ -137,7 +137,7 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_iterate(
     return 1;
   }
   // Must be between 0xc2 and 0xf4 inclusive to be valid
-  if ((uc - 0xc2) > (0xf4-0xc2)) return UTF8PROC_ERROR_INVALIDUTF8;
+  if ((utf8proc_uint32_t)(uc - 0xc2) > (0xf4-0xc2)) return UTF8PROC_ERROR_INVALIDUTF8;
   if (uc < 0xe0) {         // 2-byte sequence
      // Must have valid continuation character
      if (str >= end || !utf_cont(*str)) return UTF8PROC_ERROR_INVALIDUTF8;
@@ -290,10 +290,14 @@ static utf8proc_bool grapheme_break_simple(int lbc, int tbc) {
 
 static utf8proc_bool grapheme_break_extended(int lbc, int tbc, utf8proc_int32_t *state)
 {
-  int lbc_override = ((state && *state != UTF8PROC_BOUNDCLASS_START)
-                      ? *state : lbc);
-  utf8proc_bool break_permitted = grapheme_break_simple(lbc_override, tbc);
   if (state) {
+    int lbc_override;
+    if (*state == UTF8PROC_BOUNDCLASS_START)
+      *state = lbc_override = lbc;
+    else
+      lbc_override = *state;
+    utf8proc_bool break_permitted = grapheme_break_simple(lbc_override, tbc);
+
     // Special support for GB 12/13 made possible by GB999. After two RI
     // class codepoints we want to force a break. Do this by resetting the
     // second RI's bound class to UTF8PROC_BOUNDCLASS_OTHER, to force a break
@@ -312,8 +316,11 @@ static utf8proc_bool grapheme_break_extended(int lbc, int tbc, utf8proc_int32_t
     }
     else
       *state = tbc;
+
+    return break_permitted;
   }
-  return break_permitted;
+  else
+    return grapheme_break_simple(lbc, tbc);
 }
 
 UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break_stateful(
@@ -349,9 +356,9 @@ static utf8proc_int32_t seqindex_decode_index(const utf8proc_uint32_t seqindex)
 
 static utf8proc_ssize_t seqindex_write_char_decomposed(utf8proc_uint16_t seqindex, utf8proc_int32_t *dst, utf8proc_ssize_t bufsize, utf8proc_option_t options, int *last_boundclass) {
   utf8proc_ssize_t written = 0;
-  const utf8proc_uint16_t *entry = &utf8proc_sequences[seqindex & 0x1FFF];
-  int len = seqindex >> 13;
-  if (len >= 7) {
+  const utf8proc_uint16_t *entry = &utf8proc_sequences[seqindex & 0x3FFF];
+  int len = seqindex >> 14;
+  if (len >= 3) {
     len = *entry;
     entry++;
   }
@@ -369,19 +376,31 @@ static utf8proc_ssize_t seqindex_write_char_decomposed(utf8proc_uint16_t seqinde
 UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_tolower(utf8proc_int32_t c)
 {
   utf8proc_int32_t cl = utf8proc_get_property(c)->lowercase_seqindex;
-  return cl != UINT16_MAX ? seqindex_decode_index(cl) : c;
+  return cl != UINT16_MAX ? seqindex_decode_index((utf8proc_uint32_t)cl) : c;
 }
 
 UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_toupper(utf8proc_int32_t c)
 {
   utf8proc_int32_t cu = utf8proc_get_property(c)->uppercase_seqindex;
-  return cu != UINT16_MAX ? seqindex_decode_index(cu) : c;
+  return cu != UINT16_MAX ? seqindex_decode_index((utf8proc_uint32_t)cu) : c;
 }
 
 UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_totitle(utf8proc_int32_t c)
 {
   utf8proc_int32_t cu = utf8proc_get_property(c)->titlecase_seqindex;
-  return cu != UINT16_MAX ? seqindex_decode_index(cu) : c;
+  return cu != UINT16_MAX ? seqindex_decode_index((utf8proc_uint32_t)cu) : c;
+}
+
+UTF8PROC_DLLEXPORT int utf8proc_islower(utf8proc_int32_t c)
+{
+  const utf8proc_property_t *p = utf8proc_get_property(c);
+  return p->lowercase_seqindex != p->uppercase_seqindex && p->lowercase_seqindex == UINT16_MAX;
+}
+
+UTF8PROC_DLLEXPORT int utf8proc_isupper(utf8proc_int32_t c)
+{
+  const utf8proc_property_t *p = utf8proc_get_property(c);
+  return p->lowercase_seqindex != p->uppercase_seqindex && p->uppercase_seqindex == UINT16_MAX && p->category != UTF8PROC_CATEGORY_LT;
 }
 
 /* return a character width analogous to wcwidth (except portable and
@@ -391,7 +410,7 @@ UTF8PROC_DLLEXPORT int utf8proc_charwidth(utf8proc_int32_t c) {
 }
 
 UTF8PROC_DLLEXPORT utf8proc_category_t utf8proc_category(utf8proc_int32_t c) {
-  return utf8proc_get_property(c)->category;
+  return (utf8proc_category_t) utf8proc_get_property(c)->category;
 }
 
 UTF8PROC_DLLEXPORT const char *utf8proc_category_string(utf8proc_int32_t c) {
@@ -401,7 +420,7 @@ UTF8PROC_DLLEXPORT const char *utf8proc_category_string(utf8proc_int32_t c) {
 
 #define utf8proc_decompose_lump(replacement_uc) \
   return utf8proc_decompose_char((replacement_uc), dst, bufsize, \
-  options & ~UTF8PROC_LUMP, last_boundclass)
+  options & ~(unsigned int)UTF8PROC_LUMP, last_boundclass)
 
 UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(utf8proc_int32_t uc, utf8proc_int32_t *dst, utf8proc_ssize_t bufsize, utf8proc_option_t options, int *last_boundclass) {
   const utf8proc_property_t *property;
@@ -716,7 +735,7 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map_custom(
   *dstptr = NULL;
   result = utf8proc_decompose_custom(str, strlen, NULL, 0, options, custom_func, custom_data);
   if (result < 0) return result;
-  buffer = (utf8proc_int32_t *) malloc(result * sizeof(utf8proc_int32_t) + 1);
+  buffer = (utf8proc_int32_t *) malloc(((utf8proc_size_t)result) * sizeof(utf8proc_int32_t) + 1);
   if (!buffer) return UTF8PROC_ERROR_NOMEM;
   result = utf8proc_decompose_custom(str, strlen, buffer, result, options, custom_func, custom_data);
   if (result < 0) {

data/dependencies/utf8proc/utf8proc.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2018 Steven G. Johnson, Jiahao Chen, Peter Colberg, Tony Kelman, Scott P. Jones, and other contributors.
+ * Copyright (c) 2014-2021 Steven G. Johnson, Jiahao Chen, Peter Colberg, Tony Kelman, Scott P. Jones, and other contributors.
  * Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
@@ -27,8 +27,8 @@
  *
  * utf8proc is a free/open-source (MIT/expat licensed) C library
  * providing Unicode normalization, case-folding, and other operations
- * for strings in the UTF-8 encoding, supporting Unicode version
- * 9.0.0.  See the utf8proc home page (http://julialang.org/utf8proc/)
+ * for strings in the UTF-8 encoding, supporting up-to-date Unicode versions.
+ * See the utf8proc home page (http://julialang.org/utf8proc/)
  * for downloads and other information, or the source code on github
  * (https://github.com/JuliaLang/utf8proc).
  *
@@ -71,7 +71,7 @@
 /** The MAJOR version number (increased when backwards API compatibility is broken). */
 #define UTF8PROC_VERSION_MAJOR 2
 /** The MINOR version number (increased when new functionality is added in a backwards-compatible manner). */
-#define UTF8PROC_VERSION_MINOR 4
+#define UTF8PROC_VERSION_MINOR 7
 /** The PATCH version (increased for fixes that do not change the API). */
 #define UTF8PROC_VERSION_PATCH 0
 /** @} */
@@ -502,7 +502,7 @@ UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(
  * string and orders the decomposed sequences correctly.
  *
  * If the @ref UTF8PROC_NULLTERM flag in `options` is set, processing
- * will be stopped, when a NULL byte is encounted, otherwise `strlen`
+ * will be stopped, when a NULL byte is encountered, otherwise `strlen`
  * bytes are processed.  The result (in the form of 32-bit unicode
  * codepoints) is written into the buffer being pointed to by
  * `buffer` (which must contain at least `bufsize` entries).  In case of
@@ -635,6 +635,18 @@ UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_toupper(utf8proc_int32_t c);
  */
 UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_totitle(utf8proc_int32_t c);
 
+/**
+ * Given a codepoint `c`, return `1` if the codepoint corresponds to a lower-case character
+ * and `0` otherwise.
+ */
+UTF8PROC_DLLEXPORT int utf8proc_islower(utf8proc_int32_t c);
+
+/**
+ * Given a codepoint `c`, return `1` if the codepoint corresponds to an upper-case character
+ * and `0` otherwise.
+ */
+UTF8PROC_DLLEXPORT int utf8proc_isupper(utf8proc_int32_t c);
+
 /**
  * Given a codepoint, return a character width analogous to `wcwidth(codepoint)`,
  * except that a width of 0 is returned for non-printable codepoints