+++ /dev/null
-/* Pango
- * indic-xft.c:
- *
- * Copyright (C) 2001, 2002 IBM Corporation
- * Author: Eric Mader <mader@jtcsv.com>
- * Based on arabic-xft.c by Owen Taylor <otaylor@redhat.com>
- *
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Library General Public
- * License as published by the Free Software Foundation; either
- * version 2 of the License, or (at your option) any later version.
- *
- * This library is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * Library General Public License for more details.
- *
- * You should have received a copy of the GNU Library General Public
- * License along with this library; if not, write to the
- * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
- */
-
-#include "config.h"
-
-#include <string.h>
-
-#include "indic-ot.h"
-
-#include "pango-engine.h"
-#include "pango-ot.h"
-#include "pango-utils.h"
-#include "pangofc-font.h"
-
-typedef struct _PangoIndicInfo PangoIndicInfo;
-
-typedef struct _IndicEngineFc IndicEngineFc;
-typedef PangoEngineShapeClass IndicEngineFcClass ; /* No extra fields needed */
-
-struct _IndicEngineFc
-{
- PangoEngineShape shapeEngine;
- const IndicOTClassTable *classTable;
-};
-
-#define ENGINE_SUFFIX "ScriptEngineFc"
-#define RENDER_TYPE PANGO_RENDER_TYPE_FC
-
-#define INDIC_ENGINE_INFO(script) {#script ENGINE_SUFFIX, PANGO_ENGINE_TYPE_SHAPE, RENDER_TYPE, script##_scripts, G_N_ELEMENTS(script##_scripts)}
-
-#define INDIC_OT_CLASS_TABLE(script) &script##_class_table
-
-static PangoEngineScriptInfo deva_scripts[] = {
- { PANGO_SCRIPT_DEVANAGARI, "*" }
-};
-
-static PangoEngineScriptInfo beng_scripts[] = {
- {PANGO_SCRIPT_BENGALI, "*" }
-};
-
-static PangoEngineScriptInfo guru_scripts[] = {
- { PANGO_SCRIPT_GURMUKHI, "*" }
-};
-
-static PangoEngineScriptInfo gujr_scripts[] = {
- { PANGO_SCRIPT_GUJARATI, "*" }
-};
-
-static PangoEngineScriptInfo orya_scripts[] = {
- { PANGO_SCRIPT_ORIYA, "*" }
-};
-
-static PangoEngineScriptInfo taml_scripts[] = {
- { PANGO_SCRIPT_TAMIL, "*" }
-};
-
-static PangoEngineScriptInfo telu_scripts[] = {
- { PANGO_SCRIPT_TELUGU, "*" }
-};
-
-static PangoEngineScriptInfo knda_scripts[] = {
- { PANGO_SCRIPT_KANNADA, "*" }
-};
-
-static PangoEngineScriptInfo mlym_scripts[] = {
- { PANGO_SCRIPT_MALAYALAM, "*" }
-};
-
-static PangoEngineScriptInfo sinh_scripts[] = {
- { PANGO_SCRIPT_SINHALA, "*" }
-};
-
-static PangoEngineInfo script_engines[] = {
- INDIC_ENGINE_INFO(deva), INDIC_ENGINE_INFO(beng), INDIC_ENGINE_INFO(guru),
- INDIC_ENGINE_INFO(gujr), INDIC_ENGINE_INFO(orya), INDIC_ENGINE_INFO(taml),
- INDIC_ENGINE_INFO(telu), INDIC_ENGINE_INFO(knda), INDIC_ENGINE_INFO(mlym),
- INDIC_ENGINE_INFO(sinh)
-};
-
-/*
- * WARNING: These entries need to be in the same order as the entries
- * in script_engines[].
- *
- * FIXME: remove this requirement, either by encapsulating the order
- * in a macro that calls a body macro that can be redefined, or by
- * putting the pointers to the PangoEngineInfo in PangoIndicInfo...
- */
-static const IndicOTClassTable *indic_ot_class_tables[] = {
- INDIC_OT_CLASS_TABLE(deva), INDIC_OT_CLASS_TABLE(beng), INDIC_OT_CLASS_TABLE(guru),
- INDIC_OT_CLASS_TABLE(gujr), INDIC_OT_CLASS_TABLE(orya), INDIC_OT_CLASS_TABLE(taml),
- INDIC_OT_CLASS_TABLE(telu), INDIC_OT_CLASS_TABLE(knda), INDIC_OT_CLASS_TABLE(mlym),
- INDIC_OT_CLASS_TABLE(sinh)
-};
-
-static const PangoOTFeatureMap gsub_features[] =
-{
- {"ccmp", PANGO_OT_ALL_GLYPHS},
- {"locl", PANGO_OT_ALL_GLYPHS},
- {"init", init},
- {"nukt", nukt},
- {"akhn", akhn},
- {"rphf", rphf},
- {"blwf", blwf},
- {"half", half},
- {"pstf", pstf},
- {"vatu", vatu},
- {"pres", pres},
- {"blws", blws},
- {"abvs", abvs},
- {"psts", psts},
- {"haln", haln},
- {"calt", PANGO_OT_ALL_GLYPHS}
-};
-
-static const PangoOTFeatureMap gpos_features[] =
-{
- {"blwm", blwm},
- {"abvm", abvm},
- {"dist", dist},
- {"kern", PANGO_OT_ALL_GLYPHS},
- {"mark", PANGO_OT_ALL_GLYPHS},
- {"mkmk", PANGO_OT_ALL_GLYPHS}
-};
-
-static void
-set_glyphs (PangoFont *font,
- const gunichar *wcs,
- gulong *tags,
- glong n_glyphs,
- PangoOTBuffer *buffer,
- gboolean process_zwj)
-{
- gint i;
- PangoFcFont *fc_font;
-
- g_assert (font);
-
- fc_font = PANGO_FC_FONT (font);
-
- for (i = 0; i < n_glyphs; i++)
- {
- guint glyph;
-
- if (pango_is_zero_width (wcs[i]) &&
- (!process_zwj || wcs[i] != 0x200D))
- glyph = PANGO_GLYPH_EMPTY;
- else
- {
- glyph = pango_fc_font_get_glyph (fc_font, wcs[i]);
-
- if (!glyph)
- glyph = PANGO_GET_UNKNOWN_GLYPH ( wcs[i]);
- }
- pango_ot_buffer_add_glyph (buffer, glyph, tags[i], i);
- }
-}
-
-/*
- * FIXME: should this check for null pointers, etc.?
- */
-static gunichar *
-expand_text(const gchar *text, glong length, glong **offsets, glong *n_chars)
-{
- const gchar *p;
- gunichar *wcs, *wco;
- glong i, *oo;
-
- *n_chars = g_utf8_strlen (text, length);
- wcs = g_new (gunichar, *n_chars);
- *offsets = g_new (glong, *n_chars + 1);
-
- p = text;
- wco = wcs;
- oo = *offsets;
- for (i = 0; i < *n_chars; i++)
- {
- *wco++ = g_utf8_get_char (p);
- *oo++ = p - text;
-
- p = g_utf8_next_char (p);
- }
-
- *oo = p - text;
-
- return wcs;
-}
-
-
-/* analysis->shape_engine has the PangoEngine... */
-static void
-indic_engine_shape (PangoEngineShape *engine,
- PangoFont *font,
- const char *text,
- gint length,
- const PangoAnalysis *analysis,
- PangoGlyphString *glyphs)
-{
- PangoFcFont *fc_font;
- FT_Face face;
- PangoOTRulesetDescription desc;
- const PangoOTRuleset *ruleset;
- PangoOTBuffer *buffer;
- glong i, n_chars, n_glyphs;
- gulong *tags = NULL;
- gunichar *wc_in = NULL, *wc_out = NULL;
- glong *utf8_offsets = NULL;
- glong *indices = NULL;
- IndicEngineFc *indic_shape_engine = NULL;
- MPreFixups *mprefixups;
-
- g_return_if_fail (font != NULL);
- g_return_if_fail (text != NULL);
- g_return_if_fail (length >= 0);
- g_return_if_fail (analysis != NULL);
-
- fc_font = PANGO_FC_FONT (font);
- face = pango_fc_font_lock_face (fc_font);
- if (!face)
- return;
-
- indic_shape_engine = (IndicEngineFc *) engine;
-
- wc_in = expand_text (text, length, &utf8_offsets, &n_chars);
-
- n_glyphs = indic_ot_reorder (wc_in, utf8_offsets, n_chars, indic_shape_engine->classTable, NULL, NULL, NULL, NULL);
-
- wc_out = g_new (gunichar, n_glyphs);
- indices = g_new (glong, n_glyphs);
- tags = g_new (gulong, n_glyphs);
-
- n_glyphs = indic_ot_reorder (wc_in, utf8_offsets, n_chars, indic_shape_engine->classTable, wc_out, indices, tags, &mprefixups);
-
- pango_glyph_string_set_size (glyphs, n_glyphs);
- buffer = pango_ot_buffer_new (fc_font);
- pango_ot_buffer_set_rtl (buffer, analysis->level % 2 != 0);
-
- set_glyphs(font, wc_out, tags, n_glyphs, buffer,
- (indic_shape_engine->classTable->scriptFlags & SF_PROCESS_ZWJ) != 0);
-
- desc.script = analysis->script;
- desc.language = analysis->language;
-
- desc.n_static_gsub_features = G_N_ELEMENTS (gsub_features);
- desc.static_gsub_features = gsub_features;
- desc.n_static_gpos_features = G_N_ELEMENTS (gpos_features);
- desc.static_gpos_features = gpos_features;
-
- /* TODO populate other_features from analysis->extra_attrs */
- desc.n_other_features = 0;
- desc.other_features = NULL;
-
- ruleset = pango_ot_ruleset_get_for_description (pango_ot_info_get (face), &desc);
-
- /* do gsub processing */
- pango_ot_ruleset_substitute (ruleset, buffer);
-
- /* Fix pre-modifiers for some scripts before base consonant */
- if (mprefixups)
- {
- indic_mprefixups_apply (mprefixups, buffer);
- indic_mprefixups_free (mprefixups);
- }
-
- /* do gpos processing */
- pango_ot_ruleset_position (ruleset, buffer);
-
- pango_ot_buffer_output (buffer, glyphs);
-
- /* Get the right log_clusters values */
- for (i = 0; i < glyphs->num_glyphs; i += 1)
- glyphs->log_clusters[i] = indices[glyphs->log_clusters[i]];
-
- pango_fc_font_unlock_face (fc_font);
-
- pango_ot_buffer_destroy (buffer);
- g_free (tags);
- g_free (indices);
- g_free (wc_out);
- g_free (wc_in);
- g_free (utf8_offsets);
-}
-
-static void
-indic_engine_fc_class_init (PangoEngineShapeClass *class)
-{
- class->script_shape = indic_engine_shape;
-}
-
-PANGO_ENGINE_SHAPE_DEFINE_TYPE (IndicEngineFc, indic_engine_fc,
- indic_engine_fc_class_init, NULL)
-
-void
-PANGO_MODULE_ENTRY(init) (GTypeModule *module)
-{
- indic_engine_fc_register_type (module);
-}
-
-void
-PANGO_MODULE_ENTRY(exit) (void)
-{
-}
-
-void
-PANGO_MODULE_ENTRY(list) (PangoEngineInfo **engines,
- int *n_engines)
-{
- *engines = script_engines;
- *n_engines = G_N_ELEMENTS (script_engines);
-}
-
-PangoEngine *
-PANGO_MODULE_ENTRY(create) (const char *id)
-{
- guint i;
-
- for (i = 0; i < G_N_ELEMENTS(script_engines); i += 1)
- {
- if (!strcmp(id, script_engines[i].id))
- {
- IndicEngineFc *engine = g_object_new (indic_engine_fc_type, NULL);
- engine->classTable = indic_ot_class_tables[i];
-
- return (PangoEngine *)engine;
- }
- }
-
- return NULL;
-}
+++ /dev/null
-/* Pango
- * indic-ot-class-tables.c:
- *
- * Copyright (C) 2001, 2002 IBM Corporation. All Rights Reserved.
- * Author: Eric Mader <mader@jtcsv.com>
- *
- * Permission is hereby granted, free of charge, to any person
- * obtaining a copy of this software and associated documentation
- * files (the "Software"), to deal in the Software without
- * restriction, including without limitation the rights to use, copy,
- * modify, merge, publish, distribute, and/or sell copies of the
- * Software, and to permit persons to whom the Software is furnished
- * to do so, provided that the above copyright notice(s) and this
- * permission notice appear in all copies of the Software and that
- * both the above copyright notice(s) and this permission notice
- * appear in supporting documentation.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE
- * COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS NOTICE BE LIABLE FOR
- * ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY
- * DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
- * WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
- * ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
- * OF THIS SOFTWARE.
- *
- * Except as contained in this notice, the name of a copyright holder
- * shall not be used in advertising or otherwise to promote the sale,
- * use or other dealings in this Software without prior written
- * authorization of the copyright holder.
- */
-
-#include "config.h"
-
-#include "indic-ot.h"
-
-
-/*
- * Split matra table indices
- */
-#define _x1 (1 << CF_INDEX_SHIFT)
-#define _x2 (2 << CF_INDEX_SHIFT)
-#define _x3 (3 << CF_INDEX_SHIFT)
-#define _x4 (4 << CF_INDEX_SHIFT)
-#define _x5 (5 << CF_INDEX_SHIFT)
-#define _x6 (6 << CF_INDEX_SHIFT)
-#define _x7 (7 << CF_INDEX_SHIFT)
-#define _x8 (8 << CF_INDEX_SHIFT)
-#define _x9 (9 << CF_INDEX_SHIFT)
-
-/*
- * Simple classes
- */
-#define _xx (CC_RESERVED)
-#define _ma (CC_MODIFYING_MARK_ABOVE)
-#define _mp (CC_MODIFYING_MARK_POST)
-#define _iv (CC_INDEPENDENT_VOWEL)
-#define _ct (CC_CONSONANT | CF_CONSONANT)
-#define _cn (CC_CONSONANT_WITH_NUKTA | CF_CONSONANT)
-#define _nu (CC_NUKTA)
-#define _dv (CC_DEPENDENT_VOWEL)
-#define _dl (_dv | CF_MATRA_PRE)
-#define _db (_dv | CF_MATRA_BELOW)
-#define _da (_dv | CF_MATRA_ABOVE)
-#define _dr (_dv | CF_MATRA_POST)
-#define _lm (_dv | CF_LENGTH_MARK)
-#define _vr (CC_VIRAMA)
-#define _al (CC_AL_LAKUNA)
-
-/*
- * Split matras
- */
-#define _s1 (_dv | _x1)
-#define _s2 (_dv | _x2)
-#define _s3 (_dv | _x3)
-#define _s4 (_dv | _x4)
-#define _s5 (_dv | _x5)
-#define _s6 (_dv | _x6)
-#define _s7 (_dv | _x7)
-#define _s8 (_dv | _x8)
-#define _s9 (_dv | _x9)
-
-/*
- * consonants with special forms
- * NOTE: this assumes that no consonants with nukta have
- * special forms... (Bengali RA?)
- */
-#define _bb (_ct | CF_BELOW_BASE)
-#define _pb (_ct | CF_POST_BASE)
-#define _vt (_bb | CF_VATTU)
-#define _rv (_vt | CF_REPH)
-#define _rp (_pb | CF_REPH)
-#define _rb (_bb | CF_REPH)
-
-
-/*
- * Character class tables
- */
-static const IndicOTCharClass devaCharClasses[] =
-{
- _xx, _ma, _ma, _mp, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _iv, /* 0900 - 090F */
- _iv, _iv, _iv, _iv, _iv, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, /* 0910 - 091F */
- _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _cn, _ct, _ct, _ct, _ct, _ct, _ct, /* 0920 - 092F */
- _rv, _cn, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _xx, _xx, _nu, _xx, _dr, _dl, /* 0930 - 093F */
- _dr, _db, _db, _db, _db, _da, _da, _da, _da, _dr, _dr, _dr, _dr, _vr, _xx, _xx, /* 0940 - 094F */
- _xx, _xx, _db, _da, _da, _xx, _xx, _xx, _cn, _cn, _cn, _cn, _cn, _cn, _cn, _cn, /* 0950 - 095F */
- _iv, _iv, _db, _db, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, /* 0960 - 096F */
- _xx, _xx, _iv, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _ct, _ct, _ct, _ct, _ct /* 0970 - 097F */
-};
-
-/* As a hack, BENGALI LETTER A (U+0985) and BENGALI LETTER E (U+098F)
- * are marked as consonants below; this gives approximately the
- * right behavior for the sequences "a halant ya aa" and
- * "e halant ya aa".
- */
-static const IndicOTCharClass bengCharClasses[] =
-{
- _xx, _ma, _mp, _mp, _xx, _ct, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _xx, _xx, _ct, /* 0980 - 098F */
- _iv, _xx, _xx, _iv, _iv, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, /* 0990 - 099F */
- _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _xx, _ct, _ct, _bb, _ct, _ct, _pb, /* 09A0 - 09AF */
- _rv, _xx, _ct, _xx, _xx, _xx, _ct, _ct, _ct, _ct, _xx, _xx, _nu, _xx, _dr, _dl, /* 09B0 - 09BF */
- _dr, _db, _db, _db, _db, _xx, _xx, _dl, _dl, _xx, _xx, _s1, _s2, _vr, _xx, _xx, /* 09C0 - 09CF */
- _xx, _xx, _xx, _xx, _xx, _xx, _xx, _dr, _xx, _xx, _xx, _xx, _cn, _cn, _xx, _cn, /* 09D0 - 09DF */
- _iv, _iv, _db, _db, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, /* 09E0 - 09EF */
- _rv, _ct, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx /* 09F0 - 09FA */
-};
-
-static const IndicOTCharClass guruCharClasses[] =
-{
- _xx, _ma, _ma, _mp, _xx, _iv, _iv, _iv, _iv, _iv, _iv, _xx, _xx, _xx, _xx, _iv, /* 0A00 - 0A0F */
- _iv, _xx, _xx, _iv, _iv, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, /* 0A10 - 0A1F */
- _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _xx, _ct, _ct, _ct, _ct, _ct, _bb, /* 0A20 - 0A2F */
- _vt, _xx, _ct, _cn, _xx, _bb, _cn, _xx, _ct, _bb, _xx, _xx, _nu, _xx, _dr, _dl, /* 0A30 - 0A3F */
- _dr, _db, _db, _xx, _xx, _xx, _xx, _da, _da, _xx, _xx, _da, _da, _vr, _xx, _xx, /* 0A40 - 0A4F */
- _xx, _db, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _cn, _cn, _cn, _ct, _xx, _cn, _xx, /* 0A50 - 0A5F */
- _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, /* 0A60 - 0A6F */
- _ma, _ma, _iv, _iv, _xx, _db /* 0A70 - 0A75 */
-};
-
-static const IndicOTCharClass gujrCharClasses[] =
-{
- _xx, _ma, _ma, _mp, _xx, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _xx, _iv, _xx, _iv, /* 0A80 - 0A8F */
- _iv, _iv, _xx, _iv, _iv, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, /* 0A90 - 0A9F */
- _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _xx, _ct, _ct, _ct, _ct, _ct, _ct, /* 0AA0 - 0AAF */
- _rv, _xx, _ct, _ct, _xx, _ct, _ct, _ct, _ct, _ct, _xx, _xx, _nu, _xx, _dr, _dl, /* 0AB0 - 0ABF */
- _dr, _db, _db, _db, _db, _da, _xx, _da, _da, _dr, _xx, _dr, _dr, _vr, _xx, _xx, /* 0AC0 - 0ACF */
- _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, /* 0AD0 - 0ADF */
- _iv, _xx, _db, _db, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx /* 0AE0 - 0AEF */
-};
-
-static const IndicOTCharClass oryaCharClasses[] =
-{
- _xx, _ma, _mp, _mp, _xx, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _xx, _xx, _iv, /* 0B00 - 0B0F */
- _iv, _xx, _xx, _iv, _iv, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _ct, _bb, /* 0B10 - 0B1F */
- _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _xx, _bb, _bb, _bb, _bb, _bb, _pb, /* 0B20 - 0B2F */
- _rb, _xx, _bb, _bb, _xx, _bb, _bb, _bb, _bb, _bb, _xx, _xx, _nu, _xx, _dr, _da, /* 0B30 - 0B3F */
- _dr, _db, _db, _db, _db, _xx, _xx, _dl, _s1, _xx, _xx, _s2, _s3, _vr, _xx, _xx, /* 0B40 - 0B4F */
- _xx, _xx, _xx, _xx, _xx, _xx, _da, _dr, _xx, _xx, _xx, _xx, _cn, _cn, _xx, _pb, /* 0B50 - 0B5F */
- _iv, _iv, _db, _db, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, /* 0B60 - 0B6F */
- _xx, _bb /* 0B70 - 0B71 */
-};
-
-static const IndicOTCharClass tamlCharClasses[] =
-{
- _xx, _xx, _ma, _xx, _xx, _iv, _iv, _iv, _iv, _iv, _iv, _xx, _xx, _xx, _iv, _iv, /* 0B80 - 0B8F */
- _iv, _xx, _iv, _iv, _iv, _ct, _xx, _xx, _xx, _ct, _ct, _xx, _ct, _xx, _ct, _ct, /* 0B90 - 0B9F */
- _xx, _xx, _xx, _ct, _ct, _xx, _xx, _xx, _ct, _ct, _ct, _xx, _xx, _xx, _ct, _ct, /* 0BA0 - 0BAF */
- _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _xx, _xx, _xx, _xx, _dr, _dr, /* 0BB0 - 0BBF */
- _da, _dr, _dr, _xx, _xx, _xx, _dl, _dl, _dl, _xx, _s1, _s2, _s3, _vr, _xx, _xx, /* 0BC0 - 0BCF */
- _xx, _xx, _xx, _xx, _xx, _xx, _xx, _dr, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, /* 0BD0 - 0BDF */
- _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, /* 0BE0 - 0BEF */
- _xx, _xx, _xx /* 0BF0 - 0BF2 */
-};
-
-/* FIXME: Should some of the bb's be pb's? (KA, NA, MA, YA, VA, etc. (approx 13)) */
-static const IndicOTCharClass teluCharClasses[] =
-{
- _xx, _mp, _mp, _mp, _xx, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _xx, _iv, _iv, /* 0C00 - 0C0F */
- _iv, _xx, _iv, _iv, _iv, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, /* 0C10 - 0C1F */
- _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _xx, _bb, _bb, _bb, _bb, _bb, _bb, /* 0C20 - 0C2F */
- _bb, _bb, _bb, _bb, _xx, _bb, _bb, _bb, _bb, _bb, _xx, _xx, _xx, _xx, _da, _da, /* 0C30 - 0C3F */
- _da, _dr, _dr, _lm, _lm, _xx, _da, _da, _s1, _xx, _da, _da, _da, _vr, _xx, _xx, /* 0C40 - 0C4F */
- _xx, _xx, _xx, _xx, _xx, _da, _db, _xx, _bb, _bb, _xx, _xx, _xx, _xx, _xx, _xx, /* 0C50 - 0C5F */
- _iv, _iv, _lm, _lm, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, /* 0C60 - 0C6F */
- _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx /* 0C70 - 0C7F */
-};
-
-/* U+CC3 and U+CC4 are _lm here not _dr since the Kannada rendering
- * rules want them below and to the right of the entire cluster. They
- * aren't, strictly speaking, length marks, however.
- *
- * There's some information about this in:
- *
- * http://brahmi.sourceforge.net/docs/KannadaComputing.html
- */
-static const IndicOTCharClass kndaCharClasses[] =
-{
- _xx, _xx, _mp, _mp, _xx, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _xx, _iv, _iv, /* 0C80 - 0C8F */
- _iv, _xx, _iv, _iv, _iv, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, /* 0C90 - 0C9F */
- _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _bb, _xx, _bb, _bb, _bb, _bb, _bb, _bb, /* 0CA0 - 0CAF */
- _rb, _bb, _bb, _bb, _xx, _bb, _bb, _bb, _bb, _bb, _xx, _xx, _nu, _xx, _dr, _da, /* 0CB0 - 0CBF */
- _s1, _dr, _dr, _lm, _lm, _xx, _da, _s2, _s3, _xx, _s4, _s5, _da, _vr, _xx, _xx, /* 0CC0 - 0CCF */
- _xx, _xx, _xx, _xx, _xx, _lm, _lm, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _ct, _xx, /* 0CD0 - 0CDF */
- _iv, _iv, _lm, _lm, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx /* 0CE0 - 0CEF */
-};
-
-/*
- * FIXME: this is correct for old-style Malayalam (MAL) but not for reformed Malayalam (MLR)
- * FIXME: should there be a REPH for old-style Malayalam?
- */
-static const IndicOTCharClass mlymCharClasses[] =
-{
- _xx, _xx, _mp, _mp, _xx, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _xx, _iv, _iv, /* 0D00 - 0D0F */
- _iv, _xx, _iv, _iv, _iv, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, /* 0D10 - 0D1F */
- _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _xx, _ct, _ct, _ct, _ct, _ct, _pb, /* 0D20 - 0D2F */
- _cn, _cn, _ct, _ct, _ct, _pb, _ct, _ct, _ct, _ct, _xx, _xx, _xx, _xx, _dr, _dr, /* 0D30 - 0D3F */
- _dr, _dr, _dr, _dr, _dr, _xx, _dl, _dl, _dl, _xx, _s1, _s2, _s3, _vr, _xx, _xx, /* 0D40 - 0D4F */
- _xx, _xx, _xx, _xx, _xx, _xx, _xx, _dr, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, /* 0D50 - 0D5F */
- _iv, _iv, _db, _db, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, /* 0D60 - 0D6F */
- _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx /* 0D70 - 0D7F */
-};
-
-static const IndicOTCharClass sinhCharClasses[] =
-{
- _xx, _xx, _mp, _mp, _xx, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _iv, _iv, /* 0D80 - 0D8F */
- _iv, _iv, _iv, _iv, _iv, _iv, _iv, _xx, _xx, _xx, _ct, _ct, _ct, _ct, _ct, _ct, /* 0D90 - 0D9F */
- _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, /* 0DA0 - 0DAF */
- _ct, _ct, _xx, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _ct, _xx, _ct, _xx, _xx, /* 0DB0 - 0DBF */
- _ct, _ct, _ct, _ct, _ct, _ct, _ct, _xx, _xx, _xx, _al, _xx, _xx, _xx, _xx, _dr, /* 0DC0 - 0DCF */
- _dr, _dr, _da, _da, _db, _xx, _db, _xx, _dr, _dl, _s1, _dl, _s2, _s3, _s4, _dr, /* 0DD0 - 0DDF */
- _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, /* 0DE0 - 0DEF */
- _xx, _xx, _dr, _dr, _xx /* 0DF0 - 0DF4 */
-};
-
-
-/*
- * Split matra tables
- */
-static const IndicOTSplitMatra bengSplitTable[] = {{0x09C7, 0x09BE}, {0x09C7, 0x09D7}};
-
-static const IndicOTSplitMatra oryaSplitTable[] = {{0x0B47, 0x0B56}, {0x0B47, 0x0B3E}, {0x0B47, 0x0B57}};
-
-static const IndicOTSplitMatra tamlSplitTable[] = {{0x0BC6, 0x0BBE}, {0x0BC7, 0x0BBE}, {0x0BC6, 0x0BD7}};
-
-static const IndicOTSplitMatra teluSplitTable[] = {{0x0C46, 0x0C56}};
-
-static const IndicOTSplitMatra kndaSplitTable[] = {{0x0CBF, 0x0CD5}, {0x0CC6, 0x0CD5}, {0x0CC6, 0x0CD6}, {0x0CC6, 0x0CC2},
- {0x0CC6, 0x0CC2, 0x0CD5}};
-
-static const IndicOTSplitMatra mlymSplitTable[] = {{0x0D46, 0x0D3E}, {0x0D47, 0x0D3E}, {0x0D46, 0x0D57}};
-
-static const IndicOTSplitMatra sinhSplitTable[] = {{0x0DD9, 0x0DCA}, {0x0DD9, 0x0DCF}, {0x0DD9, 0x0DCF, 0x0DCA},
- {0x0DD9, 0x0DDF} };
-
-
-/*
- * Script Flags
- */
-
-/*
- * FIXME: post 'GSUB' reordering of MATRA_PRE's for Malayalam and Tamil
- * FIXME: reformed Malayalam needs to reorder VATTU to before base glyph...
- * FIXME: eyelash RA only for Devanagari??
- */
-#define DEVA_SCRIPT_FLAGS (SF_EYELASH_RA | SF_NO_POST_BASE_LIMIT)
-#define BENG_SCRIPT_FLAGS (SF_REPH_AFTER_BELOW | SF_NO_POST_BASE_LIMIT)
-#define GURU_SCRIPT_FLAGS (SF_NO_POST_BASE_LIMIT)
-#define GUJR_SCRIPT_FLAGS (SF_NO_POST_BASE_LIMIT)
-#define ORYA_SCRIPT_FLAGS (SF_REPH_AFTER_BELOW | SF_NO_POST_BASE_LIMIT)
-#define TAML_SCRIPT_FLAGS (SF_MPRE_FIXUP | SF_NO_POST_BASE_LIMIT)
-#define TELU_SCRIPT_FLAGS (SF_MATRAS_AFTER_BASE | 3)
-#define KNDA_SCRIPT_FLAGS (SF_MATRAS_AFTER_BASE | 3)
-#define MLYM_SCRIPT_FLAGS (SF_MPRE_FIXUP | SF_NO_POST_BASE_LIMIT | SF_PROCESS_ZWJ)
-#define SINH_SCRIPT_FLAGS (SF_NO_POST_BASE_LIMIT | SF_PROCESS_ZWJ)
-
-/*
- * Indic Class Tables
- */
-/* Add a little macro to compute lastChar based on size of the charClasses * table */
-#define INDIC_OT_CLASS_TABLE_DEFINE(name, firstChar, worstCaseExpansion, scriptFlags, charClasses, splitMatraTable) \
- const IndicOTClassTable name = {firstChar, firstChar + G_N_ELEMENTS (charClasses) - 1, \
- worstCaseExpansion, scriptFlags, charClasses, splitMatraTable}
-INDIC_OT_CLASS_TABLE_DEFINE (deva_class_table, 0x0900, 2, DEVA_SCRIPT_FLAGS, devaCharClasses, NULL);
-INDIC_OT_CLASS_TABLE_DEFINE (beng_class_table, 0x0980, 3, BENG_SCRIPT_FLAGS, bengCharClasses, bengSplitTable);
-INDIC_OT_CLASS_TABLE_DEFINE (guru_class_table, 0x0A00, 2, GURU_SCRIPT_FLAGS, guruCharClasses, NULL);
-INDIC_OT_CLASS_TABLE_DEFINE (gujr_class_table, 0x0A80, 2, GUJR_SCRIPT_FLAGS, gujrCharClasses, NULL);
-INDIC_OT_CLASS_TABLE_DEFINE (orya_class_table, 0x0B00, 3, ORYA_SCRIPT_FLAGS, oryaCharClasses, oryaSplitTable);
-INDIC_OT_CLASS_TABLE_DEFINE (taml_class_table, 0x0B80, 3, TAML_SCRIPT_FLAGS, tamlCharClasses, tamlSplitTable);
-INDIC_OT_CLASS_TABLE_DEFINE (telu_class_table, 0x0C00, 3, TELU_SCRIPT_FLAGS, teluCharClasses, teluSplitTable);
-INDIC_OT_CLASS_TABLE_DEFINE (knda_class_table, 0x0C80, 4, KNDA_SCRIPT_FLAGS, kndaCharClasses, kndaSplitTable);
-INDIC_OT_CLASS_TABLE_DEFINE (mlym_class_table, 0x0D00, 3, MLYM_SCRIPT_FLAGS, mlymCharClasses, mlymSplitTable);
-INDIC_OT_CLASS_TABLE_DEFINE (sinh_class_table, 0x0D80, 4, SINH_SCRIPT_FLAGS, sinhCharClasses, sinhSplitTable);
-
-const IndicOTSplitMatra *indic_ot_get_split_matra(const IndicOTClassTable *class_table, IndicOTCharClass char_class)
-{
- gint32 index = (char_class & CF_INDEX_MASK) >> CF_INDEX_SHIFT;
-
- return &class_table->splitMatraTable[index - 1];
-}
-
-gboolean indic_ot_is_vm_above(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return IS_VM_ABOVE(char_class);
-}
-
-gboolean indic_ot_is_vm_post(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return IS_VM_POST(char_class);
-}
-
-gboolean indic_ot_is_consonant(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return IS_CONSONANT(char_class);
-}
-
-gboolean indic_ot_is_reph(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return IS_REPH(char_class);
-}
-
-gboolean indic_ot_is_virama(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return (IS_VIRAMA(char_class) || IS_AL_LAKUNA(char_class));
-}
-
-gboolean indic_ot_is_al_lakuna(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return IS_AL_LAKUNA(char_class);
-}
-
-gboolean indic_ot_is_nukta(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return IS_NUKTA(char_class);
-}
-
-gboolean indic_ot_is_vattu(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return IS_VATTU(char_class);
-}
-
-gboolean indic_ot_is_matra(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return IS_MATRA(char_class);
-}
-
-gboolean indic_ot_is_split_matra(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return IS_SPLIT_MATRA(char_class);
-}
-
-gboolean indic_ot_is_m_pre(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return IS_M_PRE(char_class);
-}
-
-gboolean indic_ot_is_m_below(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return IS_M_BELOW(char_class);
-}
-
-gboolean indic_ot_is_m_above(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return IS_M_ABOVE(char_class);
-}
-
-gboolean indic_ot_is_m_post(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return IS_M_POST(char_class);
-}
-
-gboolean indic_ot_is_length_mark(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return IS_LENGTH_MARK(char_class);
-}
-
-gboolean indic_ot_has_post_or_below_base_form(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return HAS_POST_OR_BELOW_BASE_FORM(char_class);
-}
-
-gboolean indic_ot_has_post_base_form(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return HAS_POST_BASE_FORM(char_class);
-}
-
-gboolean indic_ot_has_below_base_form(const IndicOTClassTable *class_table, gunichar ch)
-{
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, ch);
-
- return HAS_BELOW_BASE_FORM(char_class);
-}
-
-IndicOTCharClass indic_ot_get_char_class(const IndicOTClassTable *class_table, gunichar ch)
-{
- if (ch == C_SIGN_ZWJ) {
- return CF_CONSONANT | CC_ZERO_WIDTH_MARK;
- }
-
- if (ch == C_SIGN_ZWNJ) {
- return CC_ZERO_WIDTH_MARK;
- }
-
- if (ch < class_table->firstChar || ch > class_table->lastChar) {
- return CC_RESERVED;
- }
-
- return class_table->charClasses[ch - class_table->firstChar];
-}
-
-static const gint8 stateTable[][CC_COUNT] =
-{
-/* xx ma mp iv ct cn nu dv vr zw al */
- { 1, 1, 1, 5, 3, 2, 1, 1, 1, 1, 1},
- {-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1},
- {-1, 6, 1, -1, -1, -1, -1, 5, 4, -1, -1},
- {-1, 6, 1, -1, -1, -1, 2, 5, 4, 10, 9},
- {-1, -1, -1, -1, 3, 2, -1, -1, -1, 8, -1},
- {-1, 6, 1, -1, -1, -1, -1, -1, -1, -1, -1},
- {-1, 7, 1, -1, -1, -1, -1, -1, -1, -1, -1},
- {-1, -1, 1, -1, -1, -1, -1, -1, -1, -1, -1},
- {-1, -1, -1, -1, 3, 2, -1, -1, -1, -1, -1},
- {-1, -1, -1, -1, -1, -1, -1, -1, -1, 8, -1},
- {-1, -1, -1, -1, -1, -1, -1, -1, 8, -1, 8}
-
-};
-
-glong indic_ot_find_syllable(const IndicOTClassTable *class_table, const gunichar *chars, glong prev, glong char_count)
-{
- glong cursor = prev;
- gint8 state = 0;
-
- while (cursor < char_count) {
- IndicOTCharClass char_class = indic_ot_get_char_class(class_table, chars[cursor]);
-
- state = stateTable[state][char_class & CF_CLASS_MASK];
-
- /*for the components of split matra*/
- if ((char_count >= cursor + 3) &&
- (chars[cursor] == 0x0DD9 && chars[cursor + 1] == 0x0DCF && chars[cursor + 2] == 0x0DCA)) { /*for 3 split matra of Sinhala*/
- return cursor + 3;
- }
- else if ((char_count >= cursor + 3) &&
- (chars[cursor] == 0x0CC6 && chars[cursor + 1] == 0x0CC2 && chars[cursor + 2] == 0x0CD5)) { /*for 3 split matra of Kannada*/
- return cursor + 3;
- }
- /*for 2 split matra*/
- else if (char_count >= cursor + 2) {
- /*for Bengali*/
- if ((chars[cursor] == 0x09C7 && chars[cursor + 1] == 0x09BE) ||
- (chars[cursor] == 0x09C7 && chars[cursor + 1] == 0x09D7) ||
- /*for Oriya*/
- (chars[cursor] == 0x0B47 && chars[cursor + 1] == 0x0B3E) ||
- (chars[cursor] == 0x0B47 && chars[cursor + 1] == 0x0B56) ||
- (chars[cursor] == 0x0B47 && chars[cursor + 1] == 0x0B57) ||
- /*for Tamil*/
- (chars[cursor] == 0x0BC6 && chars[cursor + 1] == 0x0BBE) ||
- (chars[cursor] == 0x0BC6 && chars[cursor + 1] == 0x0BD7) ||
- (chars[cursor] == 0x0BC7 && chars[cursor + 1] == 0x0BBE) ||
- /*for Malayalam*/
- (chars[cursor] == 0x0D46 && chars[cursor + 1] == 0x0D3E) ||
- (chars[cursor] == 0x0D46 && chars[cursor + 1] == 0x0D57) ||
- (chars[cursor] == 0x0D47 && chars[cursor + 1] == 0x0D3E) ||
- /*for Sinhala*/
- (chars[cursor] == 0x0DD9 && chars[cursor + 1] == 0x0DCA) ||
- (chars[cursor] == 0x0DD9 && chars[cursor + 1] == 0x0DCF) ||
- (chars[cursor] == 0x0DD9 && chars[cursor + 1] == 0x0DDF) ||
- (chars[cursor] == 0x0DDC && chars[cursor + 1] == 0x0DCA) ||
- /*for Telugu*/
- (chars[cursor] == 0x0C46 && chars[cursor + 1] == 0x0C56) ||
- /*for Kannada*/
- (chars[cursor] == 0x0CBF && chars[cursor + 1] == 0x0CD5) ||
- (chars[cursor] == 0x0CC6 && chars[cursor + 1] == 0x0CD5) ||
- (chars[cursor] == 0x0CC6 && chars[cursor + 1] == 0x0CD6) ||
- (chars[cursor] == 0x0CC6 && chars[cursor + 1] == 0x0CC2) ||
- (chars[cursor] == 0x0CCA && chars[cursor + 1] == 0x0CD5))
- return cursor + 2;
- }
-
- if (state < 0) {
- break;
- }
-
- cursor += 1;
- }
-
- return cursor;
-}
-
+++ /dev/null
-/* Pango
- * indic-ot.c:
- *
- * Copyright (C) 2001, 2002 IBM Corporation. All Rights Reserved.
- * Author: Eric Mader <mader@jtcsv.com>
- *
- * Permission is hereby granted, free of charge, to any person
- * obtaining a copy of this software and associated documentation
- * files (the "Software"), to deal in the Software without
- * restriction, including without limitation the rights to use, copy,
- * modify, merge, publish, distribute, and/or sell copies of the
- * Software, and to permit persons to whom the Software is furnished
- * to do so, provided that the above copyright notice(s) and this
- * permission notice appear in all copies of the Software and that
- * both the above copyright notice(s) and this permission notice
- * appear in supporting documentation.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE
- * COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS NOTICE BE LIABLE FOR
- * ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY
- * DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
- * WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
- * ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
- * OF THIS SOFTWARE.
- *
- * Except as contained in this notice, the name of a copyright holder
- * shall not be used in advertising or otherwise to promote the sale,
- * use or other dealings in this Software without prior written
- * authorization of the copyright holder.
- */
-
-#include "config.h"
-
-#include "indic-ot.h"
-#include "mprefixups.h"
-/*
- * FIXME: should the IndicOutput stuff be moved
- * to a separate .h and .c file just to keep the
- * clutter down here? (it's not really usefull
- * anyplace else, is it?)
- */
-struct _Output
-{
- glong fOutIndex;
-
- const glong *fOriginalOffsets;
-
- gunichar *fOutChars;
- glong *fCharIndices;
- gulong *fCharTags;
-
- gunichar fMpre;
- gunichar fMbelow;
- gunichar fMabove;
- gunichar fMpost;
- gunichar fLengthMark;
- gunichar fAlLakuna; /* to handle Al-Lakuna in sinhala split matras */
- glong fMatraIndex;
- gulong fMatraTags;
- gboolean fMatraWordStart;
- glong fMPreOutIndex;
-
- MPreFixups *fMPreFixups;
-};
-
-typedef struct _Output Output;
-
-static void initOutput(Output *output, const glong *originalOffsets, gunichar *outChars, glong *charIndices, gulong *charTags, MPreFixups *mpreFixups)
-{
- output->fOriginalOffsets = originalOffsets;
-
- output->fOutChars = outChars;
- output->fCharIndices = charIndices;
- output->fCharTags = charTags;
-
- output->fOutIndex = 0;
- output->fMatraTags = 0;
-
- output->fMpre = output->fMbelow = output->fMabove = output->fMpost = output->fLengthMark = output->fAlLakuna = 0;
-
- output->fMPreOutIndex = -1;
- output->fMPreFixups = mpreFixups;
-}
-
-static void saveMatra(Output *output, gunichar matra, IndicOTCharClass matraClass)
-{
- /* FIXME: check if already set, or if not a matra... */
- if (IS_M_PRE(matraClass)) {
- output->fMpre = matra;
- } else if (IS_M_BELOW(matraClass)) {
- output->fMbelow = matra;
- } else if (IS_M_ABOVE(matraClass)) {
- output->fMabove = matra;
- } else if (IS_M_POST(matraClass)) {
- output->fMpost = matra;
- } else if (IS_LENGTH_MARK(matraClass)) {
- output->fLengthMark = matra;
- } else if (IS_AL_LAKUNA(matraClass)) {
- output->fAlLakuna = matra;
- }
-}
-
-static void initMatra(Output *output, guint32 matraIndex, gulong matraTags, gboolean wordStart)
-{
- output->fMpre = output->fMbelow = output->fMabove = output->fMpost = output->fLengthMark = output->fAlLakuna = 0;
- output->fMPreOutIndex = -1;
- output->fMatraIndex = matraIndex;
- output->fMatraTags = matraTags;
- output->fMatraWordStart = wordStart;
-}
-
-static gboolean noteMatra(Output *output, const IndicOTClassTable *classTable, gunichar matra)
-{
- IndicOTCharClass matraClass = indic_ot_get_char_class(classTable, matra);
-
- if (IS_MATRA(matraClass)) {
- if (IS_SPLIT_MATRA(matraClass)) {
- const IndicOTSplitMatra *splitMatra = indic_ot_get_split_matra(classTable, matraClass);
- int i;
-
- for (i = 0; i < 3 && (*splitMatra)[i] != 0; i += 1) {
- gunichar piece = (*splitMatra)[i];
- IndicOTCharClass pieceClass = indic_ot_get_char_class(classTable, piece);
-
- saveMatra(output, piece, pieceClass);
- }
- } else {
- saveMatra(output, matra, matraClass);
- }
-
- return TRUE;
- } else
- return FALSE;
-}
-
-static void noteBaseConsonant(Output *output)
-{
- if (output->fMPreFixups && output->fMPreOutIndex >= 0) {
- indic_mprefixups_add(output->fMPreFixups, output->fOutIndex, output->fMPreOutIndex);
- }
-}
-
-static void writeChar(Output *output, gunichar ch, guint32 charIndex, gulong charTags)
-{
- if (output->fOutChars != NULL) {
- output->fOutChars[output->fOutIndex] = ch;
- output->fCharIndices[output->fOutIndex] = output->fOriginalOffsets[charIndex];
- output->fCharTags[output->fOutIndex] = charTags;
- }
-
- output->fOutIndex += 1;
-}
-
-static void writeMpre(Output *output)
-{
- if (output->fMpre != 0) {
- gulong tags = output->fMatraTags;
- if (output->fMatraWordStart)
- tags &= ~init;
-
- output->fMPreOutIndex = output->fOutIndex;
- writeChar(output, output->fMpre, output->fMatraIndex, tags);
- }
-}
-
-static void writeMbelow(Output *output)
-{
- if (output->fMbelow != 0) {
- writeChar(output, output->fMbelow, output->fMatraIndex, output->fMatraTags);
- }
-}
-
-static void writeMabove(Output *output)
-{
- if (output->fMabove != 0) {
- writeChar(output, output->fMabove, output->fMatraIndex, output->fMatraTags);
- }
-}
-
-static void writeMpost(Output *output)
-{
- if (output->fMpost != 0) {
- writeChar(output, output->fMpost, output->fMatraIndex, output->fMatraTags);
- }
-}
-
-static void writeLengthMark(Output *output)
-{
- if (output->fLengthMark != 0) {
- writeChar(output, output->fLengthMark, output->fMatraIndex, output->fMatraTags);
- }
-}
-
-static void writeAlLakuna(Output *output)
-{
- if (output->fAlLakuna != 0) {
- writeChar(output, output->fAlLakuna, output->fMatraIndex, output->fMatraTags);
- }
-}
-
-static glong getOutputIndex(Output *output)
-{
- return output->fOutIndex;
-}
-
-#define false 0
-#define true 1
-
-glong indic_ot_reorder(const gunichar *chars, const glong *utf8_offsets, glong char_count, const IndicOTClassTable *class_table, gunichar *out_chars, glong *char_indices, gulong *char_tags, MPreFixups **outMPreFixups)
-{
- MPreFixups *mpreFixups = NULL;
- Output output;
- glong i, prev = 0;
- gboolean last_in_word = FALSE;
-
- if (outMPreFixups && (class_table->scriptFlags & SF_MPRE_FIXUP)) {
- mpreFixups = indic_mprefixups_new (char_count);
- }
-
- initOutput(&output, utf8_offsets, out_chars, char_indices, char_tags, mpreFixups);
-
- while (prev < char_count) {
- glong syllable = indic_ot_find_syllable(class_table, chars, prev, char_count);
- glong matra, vmabove, vmpost = syllable;
-
- while (vmpost > prev && indic_ot_is_vm_post(class_table, chars[vmpost - 1])) {
- vmpost -= 1;
- }
-
- vmabove = vmpost;
- while (vmabove > prev && indic_ot_is_vm_above(class_table, chars[vmabove - 1])) {
- vmabove -= 1;
- }
-
- matra = vmabove - 1;
- initMatra(&output, prev, blwf_p, !last_in_word);
- while (noteMatra(&output, class_table, chars[matra]) &&
- matra != prev)
- matra--;
-
- last_in_word = TRUE;
- switch (indic_ot_get_char_class(class_table, chars[prev]) & CF_CLASS_MASK) {
- case CC_RESERVED:
- last_in_word = FALSE;
- /* Fall through */
- case CC_INDEPENDENT_VOWEL:
- case CC_ZERO_WIDTH_MARK:
- for (i = prev; i < syllable; i += 1) {
- writeChar(&output, chars[i], /*i*/ prev, blwf_p);
- }
-
- break;
-
- case CC_MODIFYING_MARK_ABOVE:
- case CC_MODIFYING_MARK_POST:
- case CC_NUKTA:
- case CC_VIRAMA:
- /* patch for rendering fix for Malayalam SAMVRUTHOKARA by suresh */
- if (chars[prev - 1] == 0x0D41) {
- writeChar(&output, chars[prev], prev, blwf_p);
- break;
- }
- /* end patch */
-
- case CC_AL_LAKUNA:
- writeChar(&output, C_DOTTED_CIRCLE, prev, blwf_p);
- writeChar(&output, chars[prev], prev, blwf_p);
- break;
-
- case CC_DEPENDENT_VOWEL:
- writeMpre(&output);
- writeChar(&output, C_DOTTED_CIRCLE, prev, blwf_p);
- writeMbelow(&output);
- writeMabove(&output);
- writeMpost(&output);
- writeLengthMark(&output);
- writeAlLakuna(&output);
- break;
-
- case CC_CONSONANT:
- case CC_CONSONANT_WITH_NUKTA:
- {
- guint32 length = vmabove - prev;
- glong lastConsonant = vmabove - 1;
- glong baseLimit = prev;
- glong baseConsonant, postBase, postBaseLimit;
- gboolean seenVattu, seenBelowBaseForm, supressVattu;
- glong bcSpan;
-
- /* Check for REPH at front of syllable */
- if (length > 2 && indic_ot_is_reph(class_table, chars[prev]) && indic_ot_is_virama(class_table, chars[prev + 1])) {
- baseLimit += 2;
-
- /* Check for eyelash RA, if the script supports it */
- if ((class_table->scriptFlags & SF_EYELASH_RA) != 0 &&
- chars[baseLimit] == C_SIGN_ZWJ) {
- if (length > 3) {
- baseLimit += 1;
- } else {
- baseLimit -= 2;
- }
- }
- }
-
- while (lastConsonant > baseLimit && !indic_ot_is_consonant(class_table, chars[lastConsonant])) {
- lastConsonant -= 1;
- }
-
- baseConsonant = lastConsonant;
- postBase = lastConsonant + 1;
-
- postBaseLimit = class_table->scriptFlags & SF_POST_BASE_LIMIT_MASK;
- seenVattu = false;
- seenBelowBaseForm = false;
- supressVattu = true;
-
- while (baseConsonant > baseLimit) {
- IndicOTCharClass charClass = indic_ot_get_char_class(class_table, chars[baseConsonant]);
-
- if (IS_CONSONANT(charClass)) {
- if (postBaseLimit == 0 || seenVattu ||
- (baseConsonant > baseLimit && !indic_ot_is_virama(class_table, chars[baseConsonant - 1])) ||
- !HAS_POST_OR_BELOW_BASE_FORM(charClass)) {
- break;
- }
-
- seenVattu = IS_VATTU(charClass);
-
- if (HAS_POST_BASE_FORM(charClass)) {
- if (seenBelowBaseForm) {
- break;
- }
-
- postBase = baseConsonant;
- } else if (HAS_BELOW_BASE_FORM(charClass)) {
- seenBelowBaseForm = true;
- }
-
- postBaseLimit -= 1;
- }
-
- baseConsonant -= 1;
- }
-
- /* Write Mpre */
- writeMpre(&output);
-
- /* Write eyelash RA */
- /* NOTE: baseLimit == prev + 3 iff eyelash RA present... */
- if (baseLimit == prev + 3) {
- writeChar(&output, chars[prev], prev, half_p);
- writeChar(&output, chars[prev + 1], prev /*+ 1*/, half_p);
- writeChar(&output, chars[prev + 2], prev /*+ 2*/, half_p);
- }
-
- /* write any pre-base consonants */
- supressVattu = true;
-
- for (i = baseLimit; i < baseConsonant; i += 1) {
- gunichar ch = chars[i];
- /* Applying blwf to the first consonant doesn't makes sense
- * since the below-form follows the consonant that it is
- * put under */
- gulong tag = (i == baseLimit) ? half_p : blwf_p;
- IndicOTCharClass charClass = indic_ot_get_char_class(class_table, ch);
-
- if (IS_CONSONANT(charClass)) {
- if (IS_VATTU(charClass) && supressVattu) {
- tag = nukt_p;
- }
- else if ((i + 2 < baseConsonant) && (chars[i + 2] == C_SIGN_ZWNJ)) {
- tag = nukt_p;
- }
-
- supressVattu = IS_VATTU(charClass);
- } else if (IS_VIRAMA(charClass) && chars[i + 1] == C_SIGN_ZWNJ)
- {
- tag = nukt_p;
- }
-
- writeChar(&output, ch, /*i*/ prev, tag);
- }
-
- bcSpan = baseConsonant + 1;
-
- if (bcSpan < vmabove && indic_ot_is_nukta(class_table, chars[bcSpan])) {
- bcSpan += 1;
- }
-
- if (baseConsonant == lastConsonant && bcSpan < vmabove && indic_ot_is_virama(class_table, chars[bcSpan])) {
- bcSpan += 1;
-
- if (bcSpan < vmabove && chars[bcSpan] == C_SIGN_ZWNJ) {
- bcSpan += 1;
- }
- }
-
- /* note the base consonant for post-GSUB fixups */
- noteBaseConsonant(&output);
-
- /* write base consonant */
- for (i = baseConsonant; i < bcSpan; i += 1) {
- writeChar(&output, chars[i], /*i*/ prev, nukt_p);
- }
-
- if ((class_table->scriptFlags & SF_MATRAS_AFTER_BASE) != 0) {
- gboolean is_for_0C48 = FALSE;
- if (output.fOutChars != NULL) { /*for 0x0C48 of Telugu*/
- int t;
- for (t = prev; t < syllable; t++) {
- if (chars[t] == 0x0C48) {
- writeMabove(&output);
- writeMbelow(&output);
- writeMpost(&output);
-
- is_for_0C48 = TRUE;
- break;
- }
- }
- }
-
- if (!is_for_0C48) {
- writeMbelow(&output);
- writeMabove(&output);
- writeMpost(&output);
- }
- }
-
- /* write below-base consonants */
- if (baseConsonant != lastConsonant) {
- for (i = bcSpan + 1; i < postBase; i += 1) {
- writeChar(&output, chars[i], /*i*/ prev, blwf_p);
- }
-
- if (postBase > lastConsonant) {
- /* write halant that was after base consonant */
- writeChar(&output, chars[bcSpan], /*bcSpan*/ prev, blwf_p);
- }
- }
-
- /* write Mbelow, Mabove */
- if ((class_table->scriptFlags & SF_MATRAS_AFTER_BASE) == 0) {
- writeMbelow(&output);
- writeMabove(&output);
- }
-
- if ((class_table->scriptFlags & SF_REPH_AFTER_BELOW) != 0) {
- if (baseLimit == prev + 2) {
- writeChar(&output, chars[prev], prev, rphf_p);
- writeChar(&output, chars[prev + 1], prev /*+ 1*/, rphf_p);
- }
-
- /* write VMabove */
- for (i = vmabove; i < vmpost; i += 1) {
- writeChar(&output, chars[i], /*i*/ prev, blwf_p);
- }
- }
-
- /* write post-base consonants */
- if (baseConsonant != lastConsonant) {
- if (postBase <= lastConsonant) {
- for (i = postBase; i <= lastConsonant; i += 1) {
- writeChar(&output, chars[i], /*i*/ prev, pstf_p);
- }
-
- /* write halant that was after base consonant */
- writeChar(&output, chars[bcSpan], /*bcSpan*/ prev, blwf_p);
- }
-
- /* write the training halant, if there is one */
- if (lastConsonant < matra && indic_ot_is_virama(class_table, chars[matra])) {
- writeChar(&output, chars[matra], /*matra*/ prev, nukt_p);
- }
- }
-
- /* write Mpost */
- if ((class_table->scriptFlags & SF_MATRAS_AFTER_BASE) == 0) {
- writeMpost(&output);
- }
-
- writeLengthMark(&output);
- writeAlLakuna(&output);
-
- /* write reph */
- if ((class_table->scriptFlags & SF_REPH_AFTER_BELOW) == 0) {
- if (baseLimit == prev + 2) {
- writeChar(&output, chars[prev], prev, rphf_p);
- writeChar(&output, chars[prev + 1], prev /*+ 1*/, rphf_p);
- }
-
- /* write VMabove */
- for (i = vmabove; i < vmpost; i += 1) {
- writeChar(&output, chars[i], /*i*/ prev, blwf_p);
- }
- }
-
- /* write VMpost */
- for (i = vmpost; i < syllable; i += 1) {
- writeChar(&output, chars[i], /*i*/ prev, blwf_p);
- }
-
- break;
- }
-
- default:
- break;
- }
-
-
- prev = syllable;
- }
-
- if (outMPreFixups) {
- *outMPreFixups = mpreFixups;
- }
-
- return getOutputIndex(&output);
-}
projects / platform / upstream / pango.git / commitdiff