qt6-qtbase/qtbase-introduce-emoji-segmenter-to-3rdparty-code.patch

From aa7d479be0df3e118580e87f30e061445dfb37e3 Mon Sep 17 00:00:00 2001
From: Eskil Abrahamsen Blomfeldt <eskil.abrahamsen-blomfeldt@qt.io>
Date: Fri, 02 Feb 2024 15:45:20 +0100
Subject: [PATCH] Introduce emoji-segmenter to 3rdparty code

This is a parser for emoji sequences developed by Google
which is used in multiple other projects for parsing
sequences of characters to see if they should be represented
as color emojis or as monochrome text.

[ChangeLog][Third-Party Code] Added the emoji-segmenter to
third party code, for supporting complex emoji sequences.
This can be configured using the -emojisegmenter option.

Task-number: QTBUG-111801
Change-Id: I7f87b0751415024d29f074d133850027f0003e29
Reviewed-by: Volker Hilsheimer <volker.hilsheimer@qt.io>
---

diff --git a/config_help.txt b/config_help.txt
index 039582da..417c2067 100644
--- a/config_help.txt
+++ b/config_help.txt
@@ -295,6 +295,7 @@ Gui, printing, widget options:
 
   -cups ................ Enable CUPS support [auto] (Unix only)
 
+  -emojisegmenter ...... Enable complex emoji sequences [yes]
   -fontconfig .......... Enable Fontconfig support [auto] (Unix only)
   -freetype ............ Select used FreeType [system/qt/no]
   -harfbuzz ............ Select used HarfBuzz-NG [system/qt/no]
diff --git a/src/3rdparty/emoji-segmenter/CONTRIBUTING.md b/src/3rdparty/emoji-segmenter/CONTRIBUTING.md
new file mode 100644
index 00000000..db177d4a
--- /dev/null
+++ b/src/3rdparty/emoji-segmenter/CONTRIBUTING.md
@@ -0,0 +1,28 @@
+# How to Contribute
+
+We'd love to accept your patches and contributions to this project. There are
+just a few small guidelines you need to follow.
+
+## Contributor License Agreement
+
+Contributions to this project must be accompanied by a Contributor License
+Agreement. You (or your employer) retain the copyright to your contribution;
+this simply gives us permission to use and redistribute your contributions as
+part of the project. Head over to <https://cla.developers.google.com/> to see
+your current agreements on file or to sign a new one.
+
+You generally only need to submit a CLA once, so if you've already submitted one
+(even if it was for a different project), you probably don't need to do it
+again.
+
+## Code reviews
+
+All submissions, including submissions by project members, require review. We
+use GitHub pull requests for this purpose. Consult
+[GitHub Help](https://help.github.com/articles/about-pull-requests/) for more
+information on using pull requests.
+
+## Community Guidelines
+
+This project follows
+[Google's Open Source Community Guidelines](https://opensource.google.com/conduct/).
diff --git a/src/3rdparty/emoji-segmenter/NEWS b/src/3rdparty/emoji-segmenter/NEWS
new file mode 100644
index 00000000..3fd07f1c
--- /dev/null
+++ b/src/3rdparty/emoji-segmenter/NEWS
@@ -0,0 +1,28 @@
+Overview of changes leading to 0.4.0
+Friday, November 15, 2024
+====================================
+
+* Add `make size` targe to
+  determine binary size.
+* Set has_vs for
+  emoji_keycap_sequence
+
+Overview of changes leading to 0.3.0
+Tuesday, September 5, 2024
+====================================
+
+* Add segmentation for variation
+  selector pairs, VS15 and VS16,
+  needed for font-variant-emoji.
+
+Overview of changes leading to 0.2.0
+Tuesday, Februar 20, 2024
+====================================
+
+* Change Ragel mode to -F1
+
+Overview of changes leading to 0.1.0
+Tuesday, January 29, 2019
+====================================
+
+* Initial release
diff --git a/src/3rdparty/emoji-segmenter/README.md b/src/3rdparty/emoji-segmenter/README.md
new file mode 100644
index 00000000..571a1a45
--- /dev/null
+++ b/src/3rdparty/emoji-segmenter/README.md
@@ -0,0 +1,103 @@
+Emoji Segmenter
+===
+
+This repository contains a Ragel grammar and generated C code for segmenting
+runs of text into text-presentation and emoji-presentation runs. It is currently
+used in projects such as Chromium and Pango for deciding which preferred
+presentation, color or text, a run of text should have.
+
+The goal is to stay very close to the grammar definitions in [Unicode Technical
+Standard #51](http://www.unicode.org/reports/tr51/).
+
+API
+===
+
+By including the `emoji_presentation_scanner.c` file, you will be able to call
+the following API
+
+```
+scan_emoji_presentation (emoji_text_iter_t p,
+    const emoji_text_iter_t pe,
+    bool* is_emoji,
+    bool* has_vs)
+```
+
+This API call will scan `emoji_text_iter_t p` for the next grammar-token and
+return an iterator that points to the end of the next token. An end iterator
+needs be specified as `pe` so that the scanner can compare against this and
+knows where to stop. In the reference parameter `is_emoji` it returns whether
+this token has emoji-presentation text-presentation, `has_vs` is set to true
+if the token contains a variation selector.
+
+A grammar token is either a combination of an emoji plus variation selector 15
+for text presentation, an emoji presentation sequence (emoji + VS16), an emoji
+presentation emoji or emoji sequence, or a single text presentation character.
+
+`emoji_text_iter_t` is an iterator type over a buffer of the character classes
+that are defined at the beginning of the the Ragel file, e.g. `EMOJI`,
+`EMOJI_TEXT_PRESENTATION`, `REGIONAL_INDICATOR`, `KEYCAP_BASE`, etc.
+
+By typedef'ing `emoji_text_iter_t` to your own iterator type, you can implement
+an adapter class that iterates over an input text buffer in any encoding, and on
+dereferencing returns the correct Ragel class by implementing something similar
+to the following Unicode character class to Ragel class mapping, example taken
+from Chromium:
+
+```
+char EmojiSegmentationCategory(UChar32 codepoint) {
+  // Specific ones first.
+  if (codepoint == kCombiningEnclosingKeycapCharacter)
+    return COMBINING_ENCLOSING_KEYCAP;
+  if (codepoint == kCombiningEnclosingCircleBackslashCharacter)
+    return COMBINING_ENCLOSING_CIRCLE_BACKSLASH;
+  if (codepoint == kZeroWidthJoinerCharacter)
+    return ZWJ;
+  if (codepoint == kVariationSelector15Character)
+    return VS15;
+  if (codepoint == kVariationSelector16Character)
+    return VS16;
+  if (codepoint == 0x1F3F4)
+    return TAG_BASE;
+  if ((codepoint >= 0xE0030 && codepoint <= 0xE0039) ||
+      (codepoint >= 0xE0061 && codepoint <= 0xE007A))
+    return TAG_SEQUENCE;
+  if (codepoint == 0xE007F)
+    return TAG_TERM;
+  if (Character::IsEmojiModifierBase(codepoint))
+    return EMOJI_MODIFIER_BASE;
+  if (Character::IsModifier(codepoint))
+    return EMOJI_MODIFIER;
+  if (Character::IsRegionalIndicator(codepoint))
+    return REGIONAL_INDICATOR;
+  if (Character::IsEmojiKeycapBase(codepoint))
+    return KEYCAP_BASE;
+
+  if (Character::IsEmojiEmojiDefault(codepoint))
+    return EMOJI_EMOJI_PRESENTATION;
+  if (Character::IsEmojiTextDefault(codepoint))
+    return EMOJI_TEXT_PRESENTATION;
+  if (Character::IsEmoji(codepoint))
+    return EMOJI;
+
+  // Ragel state machine will interpret unknown category as "any".
+  return kMaxEmojiScannerCategory;
+}
+```
+
+Update/Build requisites
+===
+
+You need to have ragel installed if you want to modify the grammar and generate a new C file as output.
+
+`apt-get install ragel`
+
+then run
+
+`make`
+
+to update the `emoji_presentation_scanner.c` and `emoji_presentation_scanner_vs.c` output C source file.
+
+Contributing
+===
+
+See the CONTRIBUTING.md file for how to contribute.
diff --git a/src/3rdparty/emoji-segmenter/REUSE.toml b/src/3rdparty/emoji-segmenter/REUSE.toml
new file mode 100644
index 00000000..53d2dc47
--- /dev/null
+++ b/src/3rdparty/emoji-segmenter/REUSE.toml
@@ -0,0 +1,7 @@
+version = 1
+
+[[annotations]]
+path = ["**"]
+precedence = "closest"
+SPDX-FileCopyrightText = "Copyright 2019 Google LLC"
+SPDX-License-Identifier = "Apache-2.0"
diff --git a/src/3rdparty/emoji-segmenter/emoji_presentation_scanner.c b/src/3rdparty/emoji-segmenter/emoji_presentation_scanner.c
new file mode 100644
index 00000000..00b7700a
--- /dev/null
+++ b/src/3rdparty/emoji-segmenter/emoji_presentation_scanner.c
@@ -0,0 +1,251 @@
+
+#line 1 "emoji_presentation_scanner.rl"
+/* Copyright 2019 Google LLC
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     https://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#include <stdbool.h>
+
+#ifndef EMOJI_LINKAGE
+#define EMOJI_LINKAGE static
+#endif
+
+
+#line 23 "emoji_presentation_scanner.c"
+static const unsigned char _emoji_presentation_trans_keys[] = {
+	0u, 13u, 14u, 15u, 0u, 13u, 9u, 12u, 10u, 12u, 10u, 10u, 4u, 12u, 4u, 12u, 
+	6u, 6u, 9u, 12u, 8u, 8u, 8u, 10u, 9u, 14u, 0
+};
+
+static const char _emoji_presentation_key_spans[] = {
+	14, 2, 14, 4, 3, 1, 9, 9, 
+	1, 4, 1, 3, 6
+};
+
+static const char _emoji_presentation_index_offsets[] = {
+	0, 15, 18, 33, 38, 42, 44, 54, 
+	64, 66, 71, 73, 77
+};
+
+static const char _emoji_presentation_indicies[] = {
+	1, 1, 1, 2, 0, 0, 0, 1, 
+	0, 0, 0, 0, 0, 1, 0, 4, 
+	5, 3, 6, 6, 7, 8, 9, 9, 
+	10, 11, 9, 9, 9, 9, 9, 12, 
+	9, 5, 13, 14, 15, 0, 13, 16, 
+	17, 16, 13, 0, 17, 16, 16, 16, 
+	16, 16, 13, 16, 17, 16, 17, 16, 
+	16, 16, 16, 5, 13, 14, 15, 16, 
+	5, 18, 5, 13, 19, 20, 18, 14, 
+	21, 23, 22, 13, 22, 5, 13, 14, 
+	15, 16, 4, 16, 0
+};
+
+static const char _emoji_presentation_trans_targs[] = {
+	2, 4, 6, 2, 1, 2, 3, 3, 
+	7, 2, 8, 9, 12, 0, 2, 5, 
+	2, 5, 2, 10, 11, 2, 2, 2
+};
+
+static const char _emoji_presentation_trans_actions[] = {
+	1, 2, 2, 3, 0, 4, 7, 2, 
+	2, 8, 0, 7, 2, 0, 9, 10, 
+	11, 2, 12, 0, 10, 13, 14, 15
+};
+
+static const char _emoji_presentation_to_state_actions[] = {
+	0, 0, 5, 0, 0, 0, 0, 0, 
+	0, 0, 0, 0, 0
+};
+
+static const char _emoji_presentation_from_state_actions[] = {
+	0, 0, 6, 0, 0, 0, 0, 0, 
+	0, 0, 0, 0, 0
+};
+
+static const char _emoji_presentation_eof_trans[] = {
+	1, 4, 0, 1, 17, 1, 17, 17, 
+	19, 19, 22, 23, 17
+};
+
+static const int emoji_presentation_start = 2;
+
+static const int emoji_presentation_en_text_and_emoji_run = 2;
+
+
+#line 26 "emoji_presentation_scanner.rl"
+
+
+
+#line 100 "emoji_presentation_scanner.rl"
+
+
+EMOJI_LINKAGE emoji_text_iter_t
+scan_emoji_presentation (emoji_text_iter_t p,
+    const emoji_text_iter_t pe,
+    bool* is_emoji,
+    bool* has_vs)
+{
+  emoji_text_iter_t ts;
+  emoji_text_iter_t te;
+  const emoji_text_iter_t eof = pe;
+
+  (void)ts;
+
+  unsigned act;
+  int cs;
+
+  
+#line 100 "emoji_presentation_scanner.c"
+	{
+	cs = emoji_presentation_start;
+	ts = 0;
+	te = 0;
+	act = 0;
+	}
+
+#line 106 "emoji_presentation_scanner.c"
+	{
+	int _slen;
+	int _trans;
+	const unsigned char *_keys;
+	const char *_inds;
+	if ( p == pe )
+		goto _test_eof;
+_resume:
+	switch ( _emoji_presentation_from_state_actions[cs] ) {
+	case 6:
+#line 1 "NONE"
+	{ts = p;}
+	break;
+#line 118 "emoji_presentation_scanner.c"
+	}
+
+	_keys = _emoji_presentation_trans_keys + (cs<<1);
+	_inds = _emoji_presentation_indicies + _emoji_presentation_index_offsets[cs];
+
+	_slen = _emoji_presentation_key_spans[cs];
+	_trans = _inds[ _slen > 0 && _keys[0] <=(*p) &&
+		(*p) <= _keys[1] ?
+		(*p) - _keys[0] : _slen ];
+
+_eof_trans:
+	cs = _emoji_presentation_trans_targs[_trans];
+
+	if ( _emoji_presentation_trans_actions[_trans] == 0 )
+		goto _again;
+
+	switch ( _emoji_presentation_trans_actions[_trans] ) {
+	case 9:
+#line 94 "emoji_presentation_scanner.rl"
+	{te = p+1;{ *is_emoji = false; *has_vs = true; return te; }}
+	break;
+	case 15:
+#line 95 "emoji_presentation_scanner.rl"
+	{te = p+1;{ *is_emoji = true; *has_vs = true; return te; }}
+	break;
+	case 4:
+#line 96 "emoji_presentation_scanner.rl"
+	{te = p+1;{ *is_emoji = true; *has_vs = false; return te; }}
+	break;
+	case 8:
+#line 97 "emoji_presentation_scanner.rl"
+	{te = p+1;{ *is_emoji = false; *has_vs = false; return te; }}
+	break;
+	case 13:
+#line 94 "emoji_presentation_scanner.rl"
+	{te = p;p--;{ *is_emoji = false; *has_vs = true; return te; }}
+	break;
+	case 14:
+#line 95 "emoji_presentation_scanner.rl"
+	{te = p;p--;{ *is_emoji = true; *has_vs = true; return te; }}
+	break;
+	case 11:
+#line 96 "emoji_presentation_scanner.rl"
+	{te = p;p--;{ *is_emoji = true; *has_vs = false; return te; }}
+	break;
+	case 12:
+#line 97 "emoji_presentation_scanner.rl"
+	{te = p;p--;{ *is_emoji = false; *has_vs = false; return te; }}
+	break;
+	case 3:
+#line 96 "emoji_presentation_scanner.rl"
+	{{p = ((te))-1;}{ *is_emoji = true; *has_vs = false; return te; }}
+	break;
+	case 1:
+#line 1 "NONE"
+	{	switch( act ) {
+	case 2:
+	{{p = ((te))-1;} *is_emoji = true; *has_vs = true; return te; }
+	break;
+	case 3:
+	{{p = ((te))-1;} *is_emoji = true; *has_vs = false; return te; }
+	break;
+	case 4:
+	{{p = ((te))-1;} *is_emoji = false; *has_vs = false; return te; }
+	break;
+	}
+	}
+	break;
+	case 10:
+#line 1 "NONE"
+	{te = p+1;}
+#line 95 "emoji_presentation_scanner.rl"
+	{act = 2;}
+	break;
+	case 2:
+#line 1 "NONE"
+	{te = p+1;}
+#line 96 "emoji_presentation_scanner.rl"
+	{act = 3;}
+	break;
+	case 7:
+#line 1 "NONE"
+	{te = p+1;}
+#line 97 "emoji_presentation_scanner.rl"
+	{act = 4;}
+	break;
+#line 188 "emoji_presentation_scanner.c"
+	}
+
+_again:
+	switch ( _emoji_presentation_to_state_actions[cs] ) {
+	case 5:
+#line 1 "NONE"
+	{ts = 0;}
+	break;
+#line 195 "emoji_presentation_scanner.c"
+	}
+
+	if ( ++p != pe )
+		goto _resume;
+	_test_eof: {}
+	if ( p == eof )
+	{
+	if ( _emoji_presentation_eof_trans[cs] > 0 ) {
+		_trans = _emoji_presentation_eof_trans[cs] - 1;
+		goto _eof_trans;
+	}
+	}
+
+	}
+
+#line 118 "emoji_presentation_scanner.rl"
+
+
+  /* Should not be reached. */
+  *is_emoji = false;
+  *has_vs = false;
+  return p;
+}
diff --git a/src/3rdparty/emoji-segmenter/patch/0001-Compile-with-warnings-are-errors.patch b/src/3rdparty/emoji-segmenter/patch/0001-Compile-with-warnings-are-errors.patch
new file mode 100644
index 00000000..0cc1868c
--- /dev/null
+++ b/src/3rdparty/emoji-segmenter/patch/0001-Compile-with-warnings-are-errors.patch
@@ -0,0 +1,26 @@
+From 4ced1426e27320e00b0dd28693df5d95c648d230 Mon Sep 17 00:00:00 2001
+From: Eskil Abrahamsen Blomfeldt <eskil.abrahamsen-blomfeldt@qt.io>
+Date: Thu, 14 Nov 2024 09:42:11 +0100
+Subject: [PATCH] Compile with warnings-are-errors
+
+Change-Id: Icea8febefc90f3f047143e5b76ff511145c0dcae
+---
+ src/3rdparty/emoji-segmenter/emoji_presentation_scanner.c | 2 ++
+ 1 file changed, 2 insertions(+)
+
+diff --git a/src/3rdparty/emoji-segmenter/emoji_presentation_scanner.c b/src/3rdparty/emoji-segmenter/emoji_presentation_scanner.c
+index 56e2e78033..ce7e01846c 100644
+--- a/src/3rdparty/emoji-segmenter/emoji_presentation_scanner.c
++++ b/src/3rdparty/emoji-segmenter/emoji_presentation_scanner.c
+@@ -101,6 +101,8 @@ scan_emoji_presentation (emoji_text_iter_t p,
+   emoji_text_iter_t te;
+   const emoji_text_iter_t eof = pe;
+ 
++  (void)ts;
++
+   unsigned act;
+   int cs;
+ 
+-- 
+2.40.0.windows.1
+
diff --git a/src/3rdparty/emoji-segmenter/qt_attribution.json b/src/3rdparty/emoji-segmenter/qt_attribution.json
new file mode 100644
index 00000000..64083381
--- /dev/null
+++ b/src/3rdparty/emoji-segmenter/qt_attribution.json
@@ -0,0 +1,16 @@
+{
+    "Id": "emoji-segmenter",
+    "Name": "Emoji Segmenter",
+    "QDocModule": "qtgui",
+    "QtUsage": "Used in QtGui for parsing complex emoji sequences. Can be configured using the -emojisegmenter option.",
+    "SecurityCritical": true,
+
+    "Description": "A parser for emoji sequences.",
+    "Homepage": "https://github.com/google/emoji-segmenter",
+    "Version": "0.4.0",
+    "DownloadLocation": "https://github.com/google/emoji-segmenter/releases/tag/0.4.0",
+
+    "License": "Apache License 2.0",
+    "LicenseId": "Apache-2.0",
+    "Copyright": "Copyright 2019 Google LLC"
+}
diff --git a/src/gui/configure.cmake b/src/gui/configure.cmake
index 0e53f512..44bef7d3 100644
--- a/src/gui/configure.cmake
+++ b/src/gui/configure.cmake
@@ -689,6 +689,12 @@ qt_feature("direct2d1_1" PRIVATE
     LABEL "Direct 2D 1.1"
     CONDITION QT_FEATURE_direct2d AND TEST_d2d1_1
 )
+qt_feature("emojisegmenter" PUBLIC PRIVATE
+    SECTION "Fonts"
+    LABEL "Emoji Segmenter"
+    PURPOSE "Supports parsing complex emoji sequences for better font resolution."
+)
+qt_feature_definition("emojisegmenter" "QT_NO_EMOJISEGMENTER" NEGATE VALUE "1")
 qt_feature("evdev" PRIVATE
     LABEL "evdev"
     CONDITION QT_FEATURE_thread AND TEST_evdev
@@ -1285,6 +1291,7 @@ qt_feature("wayland" PUBLIC
 
 qt_configure_add_summary_section(NAME "Qt Gui")
 qt_configure_add_summary_entry(ARGS "accessibility")
+qt_configure_add_summary_entry(ARGS "emojisegmenter")
 qt_configure_add_summary_entry(ARGS "freetype")
 qt_configure_add_summary_entry(ARGS "system-freetype")
 qt_configure_add_summary_entry(ARGS "harfbuzz")
diff --git a/src/gui/qt_cmdline.cmake b/src/gui/qt_cmdline.cmake
index 446618eb..5465b2c6 100644
--- a/src/gui/qt_cmdline.cmake
+++ b/src/gui/qt_cmdline.cmake
@@ -10,6 +10,7 @@ qt_commandline_option(eglfs TYPE boolean)
 qt_commandline_option(evdev TYPE boolean)
 qt_commandline_option(fontconfig TYPE boolean)
 qt_commandline_option(freetype TYPE enum VALUES no qt system)
+qt_commandline_option(emojisegmenter TYPE boolean)
 qt_commandline_option(gbm TYPE boolean)
 qt_commandline_option(gif TYPE boolean)
 qt_commandline_option(harfbuzz TYPE enum VALUES no qt system)