summaryrefslogtreecommitdiffstats
path: root/unicode
diff options
context:
space:
mode:
authorSam Varshavchik2020-12-06 23:17:15 -0500
committerSam Varshavchik2020-12-06 23:17:15 -0500
commite0323de90c1db71e364abc0a493f19585377d7ed (patch)
tree2c626c4b50e37975ac4f6117574dd7718bb69411 /unicode
parenta5cc76216e08481a6f3614574a8ee498e5800afa (diff)
downloadcourier-libs-e0323de90c1db71e364abc0a493f19585377d7ed.tar.bz2
courier-unicode: add original string flag to bidi_embed callback.
Diffstat (limited to 'unicode')
-rw-r--r--unicode/biditest2.C37
-rw-r--r--unicode/book.xml26
-rw-r--r--unicode/courier-unicode.h.in4
-rw-r--r--unicode/unicode_bidi.c22
-rw-r--r--unicode/unicodecpp.C14
5 files changed, 76 insertions, 27 deletions
diff --git a/unicode/biditest2.C b/unicode/biditest2.C
index ce293b6..0e0472e 100644
--- a/unicode/biditest2.C
+++ b/unicode/biditest2.C
@@ -355,9 +355,40 @@ void character_test()
0,
logical_string.size());
- auto new_string=unicode::bidi_embed(logical_string,
- logical_levels,
- paragraph);
+ std::u32string new_string;
+
+ unicode::bidi_embed
+ (logical_string,
+ logical_levels,
+ paragraph,
+ [&]
+ (const char32_t *string,
+ size_t n,
+ bool is_part_of_string)
+ {
+ if ((std::less_equal<const char32_t *>
+ {}(logical_string.c_str(),
+ string) &&
+ std::less<const
+ char32_t *>
+ {}(string,
+ logical_string.c_str()
+ +logical_string.size()))
+ != is_part_of_string)
+ {
+ std::cerr <<
+ "bidi_embed passed in "
+ "wrong value for "
+ "is_part_of_string"
+ << std::endl;
+ exit(1);
+ }
+
+ new_string.insert
+ (new_string.end(),
+ string,
+ string+n);
+ });
auto save_string=new_string;
diff --git a/unicode/book.xml b/unicode/book.xml
index 3eb0a6e..0275058 100644
--- a/unicode/book.xml
+++ b/unicode/book.xml
@@ -381,7 +381,7 @@ See COPYING for distribution information.
<paramdef>const unicode_bidi_level_t *<parameter>levels</parameter></paramdef>
<paramdef>size_t <parameter>n</parameter></paramdef>
<paramdef>unicode_bidi_level_t <parameter>paragraph_embedding</parameter></paramdef>
- <paramdef>void (*<parameter>emit</parameter>)(const char32_t *string, size_t n, void *arg)</paramdef>
+ <paramdef>void (*<parameter>emit</parameter>)(const char32_t *string, size_t n, int is_part_of_string, void *arg)</paramdef>
<paramdef>void *<parameter>arg</parameter></paramdef>
</funcprototype>
@@ -942,6 +942,14 @@ See COPYING for distribution information.
</listitem>
<listitem>
<para>
+ Indication whether the Unicode string pointer is pointing
+ to a part of the original Unicode string that's getting
+ embedded. Otherwise this must be some marker character that's
+ not present in the original Unicode string.
+ </para>
+ </listitem>
+ <listitem>
+ <para>
Forwarded <parameter>arg</parameter> pointer value.
</para>
</listitem>
@@ -2835,7 +2843,7 @@ See COPYING for distribution information.
<funcdef>int <function>unicode::bidi_reorder</function></funcdef>
<paramdef>std::u32string &amp;<parameter>string</parameter></paramdef>
<paramdef>std::vector&lt;unicode_bidi_level_t&gt; &amp;<parameter>embedding_level</parameter></paramdef>
- <paramdef>const std::function&lt;void (size_t, size_t) noexcept&gt; &amp;<parameter>reorder_callback</parameter>=[](size_t, size_t){}</paramdef>
+ <paramdef>const std::function&lt;void (size_t, size_t)&gt; &amp;<parameter>reorder_callback</parameter>=[](size_t, size_t){}</paramdef>
<paramdef>size_t <parameter>starting_pos</parameter>=0</paramdef>
<paramdef>size_t <parameter>n</parameter>=(size_t)-1</paramdef>
</funcprototype>
@@ -2843,7 +2851,7 @@ See COPYING for distribution information.
<funcprototype>
<funcdef>void <function>unicode::bidi_reorder</function></funcdef>
<paramdef>std::vector&lt;unicode_bidi_level_t&gt; &amp;<parameter>embedding_level</parameter></paramdef>
- <paramdef>const std::function&lt;void (size_t, size_t) noexcept&gt; &amp;<parameter>reorder_callback</parameter>=[](size_t, size_t){}</paramdef>
+ <paramdef>const std::function&lt;void (size_t, size_t)&gt; &amp;<parameter>reorder_callback</parameter>=[](size_t, size_t){}</paramdef>
<paramdef>size_t <parameter>starting_pos</parameter>=0</paramdef>
<paramdef>size_t <parameter>n</parameter>=(size_t)-1</paramdef>
</funcprototype>
@@ -2851,7 +2859,7 @@ See COPYING for distribution information.
<funcprototype>
<funcdef>void <function>unicode::bidi_cleanup</function></funcdef>
<paramdef>std::u32string &amp;<parameter>string</parameter></paramdef>
- <paramdef>const std::function&lt;void (size_t) noexcept&gt; &amp;<parameter>removed_callback</parameter>=[](size_t){}</paramdef>
+ <paramdef>const std::function&lt;void (size_t)&gt; &amp;<parameter>removed_callback</parameter>=[](size_t){}</paramdef>
<paramdef>int <parameter>cleanup_options</parameter></paramdef>
</funcprototype>
@@ -2859,7 +2867,7 @@ See COPYING for distribution information.
<funcdef>int <function>unicode::bidi_cleanup</function></funcdef>
<paramdef>std::u32string &amp;<parameter>string</parameter></paramdef>
<paramdef>std::vector &lt;unicode_bidi_level_t&gt; &amp;<parameter>levels</parameter></paramdef>
- <paramdef>const std::function&lt;void (size_t) noexcept&gt; &amp;<parameter>removed_callback</parameter>=[](size_t){}</paramdef>
+ <paramdef>const std::function&lt;void (size_t)&gt; &amp;<parameter>removed_callback</parameter>=[](size_t){}</paramdef>
<paramdef>int <parameter>cleanup_options</parameter>=0</paramdef>
</funcprototype>
@@ -2867,7 +2875,7 @@ See COPYING for distribution information.
<funcdef>int <function>unicode::bidi_cleanup</function></funcdef>
<paramdef>std::u32string &amp;<parameter>string</parameter></paramdef>
<paramdef>std::vector &lt;unicode_bidi_level_t&gt; &amp;<parameter>levels</parameter></paramdef>
- <paramdef>const std::function&lt;void (size_t) noexcept&gt; &amp;<parameter>removed_callback</parameter></paramdef>
+ <paramdef>const std::function&lt;void (size_t)&gt; &amp;<parameter>removed_callback</parameter></paramdef>
<paramdef>int <parameter>cleanup_options</parameter></paramdef>
<paramdef>size_t <parameter>starting_pos</parameter></paramdef>
<paramdef>size_t <parameter>n</parameter></paramdef>
@@ -2878,7 +2886,7 @@ See COPYING for distribution information.
<paramdef>std::u32string &amp;<parameter>string</parameter></paramdef>
<paramdef>std::vector &lt;unicode_bidi_level_t&gt; &amp;<parameter>levels</parameter></paramdef>
<paramdef>unicode_bidi_level_t <parameter>paragraph_embedding</parameter></paramdef>
- <paramdef>const std::function&lt;void (size_t, size_t) noexcept&gt; &amp;<parameter>reorder_callback</parameter>=[](size_t, size_t){}</paramdef>
+ <paramdef>const std::function&lt;void (size_t, size_t)&gt; &amp;<parameter>reorder_callback</parameter>=[](size_t, size_t){}</paramdef>
<paramdef>size_t <parameter>starting_pos</parameter>=0</paramdef>
<paramdef>size_t <parameter>n</parameter>=(size_t)-1</paramdef>
</funcprototype>
@@ -2887,7 +2895,7 @@ See COPYING for distribution information.
<funcdef>void <function>unicode::bidi_logical_order</function></funcdef>
<paramdef>std::vector &lt;unicode_bidi_level_t&gt; &amp;<parameter>levels</parameter></paramdef>
<paramdef>unicode_bidi_level_t <parameter>paragraph_embedding</parameter></paramdef>
- <paramdef>const std::function&lt;void (size_t, size_t) noexcept&gt; &amp;<parameter>reorder_callback</parameter></paramdef>
+ <paramdef>const std::function&lt;void (size_t, size_t)&gt; &amp;<parameter>reorder_callback</parameter></paramdef>
<paramdef>size_t <parameter>starting_pos</parameter>=0</paramdef>
<paramdef>size_t <parameter>n</parameter>=(size_t)-1</paramdef>
</funcprototype>
@@ -2897,7 +2905,7 @@ See COPYING for distribution information.
<paramdef>const std::u32string &amp;<parameter>string</parameter></paramdef>
<paramdef>const std::vector &lt;unicode_bidi_level_t&gt; &amp;<parameter>levels</parameter></paramdef>
<paramdef>unicode_bidi_level_t <parameter>paragraph_embedding</parameter></paramdef>
- <paramdef>const std::function&lt;void (size_t, const char32_t *, size_t) noexcept&gt; &amp;<parameter>callback</parameter></paramdef>
+ <paramdef>const std::function&lt;void (const char32_t *, size_t, bool)&gt; &amp;<parameter>callback</parameter></paramdef>
</funcprototype>
<funcprototype>
diff --git a/unicode/courier-unicode.h.in b/unicode/courier-unicode.h.in
index 9d398ec..1c7245c 100644
--- a/unicode/courier-unicode.h.in
+++ b/unicode/courier-unicode.h.in
@@ -698,6 +698,7 @@ extern void unicode_bidi_embed(const char32_t *string,
unicode_bidi_level_t paragraph_embedding,
void (*emit)(const char32_t *string,
size_t n,
+ int,
void *arg),
void *arg);
@@ -2313,7 +2314,8 @@ int bidi_embed(const std::u32string &string,
const std::vector<unicode_bidi_level_t> &levels,
unicode_bidi_level_t paragraph_embedding,
const std::function<void (const char32_t *string,
- size_t n)> &lambda);
+ size_t n,
+ bool is_part_of_string)> &lambda);
//! Embed directional and isolation markers
diff --git a/unicode/unicode_bidi.c b/unicode/unicode_bidi.c
index 92fe8a7..73440ed 100644
--- a/unicode/unicode_bidi.c
+++ b/unicode/unicode_bidi.c
@@ -2215,6 +2215,7 @@ static void emit_bidi_embed_levelrun(const char32_t *string,
struct need_marker_info *need_marker,
void (*emit)(const char32_t *string,
size_t n,
+ int is_part_of_string,
void *arg),
void *arg);
@@ -2250,18 +2251,19 @@ static void emit_marker(struct bidi_embed_levelrun *p,
struct need_marker_info *info,
void (*emit)(const char32_t *string,
size_t n,
+ int is_part_of_string,
void *arg),
void *arg)
{
char32_t marker= (p->level & 1) ? UNICODE_RLM:UNICODE_LRM;
if (info->need_marker)
- (*emit)(&marker, 1, arg);
+ (*emit)(&marker, 1, 0, arg);
if (info->need_pdi)
{
marker=UNICODE_PDI;
- (*emit)(&marker, 1, arg);
+ (*emit)(&marker, 1, 0, arg);
}
}
@@ -2271,6 +2273,7 @@ void unicode_bidi_embed(const char32_t *string,
unicode_bidi_level_t paragraph_level,
void (*emit)(const char32_t *string,
size_t n,
+ int is_part_of_string,
void *arg),
void *arg)
{
@@ -2404,7 +2407,7 @@ void unicode_bidi_embed(const char32_t *string,
previous_level=paragraph_level;
- (*emit)(string+p->end, 1, arg);
+ (*emit)(string+p->end, 1, 1, arg);
continue;
}
@@ -2506,6 +2509,7 @@ static void emit_bidi_embed_levelrun(const char32_t *string,
struct need_marker_info *need_marker,
void (*emit)(const char32_t *string,
size_t n,
+ int is_part_of_string,
void *arg),
void *arg)
{
@@ -2561,7 +2565,7 @@ static void emit_bidi_embed_levelrun(const char32_t *string,
char32_t override_start=run->level ? UNICODE_RLI:UNICODE_LRI;
if (run->level != paragraph_level)
- (*emit)(&override_start, 1, arg);
+ (*emit)(&override_start, 1, 0, arg);
/*
** Make sure the character sequence has strong context.
@@ -2637,9 +2641,9 @@ static void emit_bidi_embed_levelrun(const char32_t *string,
*/
if (word_start > start)
(*emit)(string+start,
- word_start-start, arg);
+ word_start-start, 1, arg);
- (*emit)(&override_start, 1, arg);
+ (*emit)(&override_start, 1, 0, arg);
while (++i < end)
{
enum_bidi_type_t t=types[i];
@@ -2657,12 +2661,12 @@ static void emit_bidi_embed_levelrun(const char32_t *string,
fprintf(DEBUGDUMP, "end of word at %d\n",
(int)i);
#endif
- (*emit)(string+word_start, i-word_start, arg);
- (*emit)(&override_end, 1, arg);
+ (*emit)(string+word_start, i-word_start, 1, arg);
+ (*emit)(&override_end, 1, 0, arg);
start=i;
continue;
}
- (*emit)(string+start, i-start, arg);
+ (*emit)(string+start, i-start, 1, arg);
start=i;
}
diff --git a/unicode/unicodecpp.C b/unicode/unicodecpp.C
index 3ef3b05..10156a4 100644
--- a/unicode/unicodecpp.C
+++ b/unicode/unicodecpp.C
@@ -857,12 +857,14 @@ void unicode::bidi_logical_order(std::vector<unicode_bidi_level_t> &levels,
extern "C" {
static void embed_callback(const char32_t *string,
size_t n,
+ int is_part_of_string,
void *arg)
{
auto p=reinterpret_cast<cb_wrapper<void
(const char32_t *,
- size_t n)> *>(arg);
- (*p)(string, n);
+ size_t n,
+ bool)> *>(arg);
+ (*p)(string, n, is_part_of_string != 0);
}
}
@@ -870,7 +872,8 @@ int unicode::bidi_embed(const std::u32string &string,
const std::vector<unicode_bidi_level_t> &levels,
unicode_bidi_level_t paragraph_embedding,
const std::function<void (const char32_t *string,
- size_t n)>
+ size_t n,
+ bool is_part_of_string)>
&lambda)
{
if (string.size() != levels.size())
@@ -879,7 +882,7 @@ int unicode::bidi_embed(const std::u32string &string,
if (string.empty())
return 0;
- cb_wrapper<void (const char32_t *, size_t)> cb{lambda};
+ cb_wrapper<void (const char32_t *, size_t, bool)> cb{lambda};
unicode_bidi_embed(&string[0], &levels[0], string.size(),
paragraph_embedding,
embed_callback,
@@ -899,7 +902,8 @@ std::u32string unicode::bidi_embed(const std::u32string &string,
(void)bidi_embed(string, levels, paragraph_embedding,
[&]
(const char32_t *string,
- size_t n)
+ size_t n,
+ bool ignored)
{
new_string.insert(new_string.end(),
string, string+n);