From adfe2fb916263ce8b57fc67d409e98da7c271bee Mon Sep 17 00:00:00 2001
From: Yuanle Song <sylecn@gmail.com>
Date: Wed, 23 Oct 2019 01:37:01 +0800
Subject: [PATCH] v0.9.0 support fuzzy pinyin.

- added FuzzyFlag property.
- updated zero-pinyin.el to support zero-pinyin-fuzzy-flag variable.
---
 ...yinService1.ZeroPinyinServiceInterface.xml |   9 ++
 main.c                                        |   4 +-
 meson.build                                   |   4 +-
 operational                                   |  96 +++++++++++++++-
 pinyin-id.h                                   |  76 +++++++++++++
 zero-pinyin-service.c                         | 105 +++++++++++++++---
 zero-pinyin-service.h                         |   6 +
 7 files changed, 280 insertions(+), 20 deletions(-)
 create mode 100644 pinyin-id.h

diff --git a/com.emacsos.zero.ZeroPinyinService1.ZeroPinyinServiceInterface.xml b/com.emacsos.zero.ZeroPinyinService1.ZeroPinyinServiceInterface.xml
index 4be7072..31c3f61 100644
--- a/com.emacsos.zero.ZeroPinyinService1.ZeroPinyinServiceInterface.xml
+++ b/com.emacsos.zero.ZeroPinyinService1.ZeroPinyinServiceInterface.xml
@@ -3,6 +3,15 @@
 "http://www.freedesktop.org/standards/dbus/1.0/introspect.dtd" >
 <node>
   <interface name="com.emacsos.zero.ZeroPinyinService1.ZeroPinyinServiceInterface">
+    <!--
+	FuzzyFlag: fuzzy matching flag for GetCandidates method.
+	0 0b0 no fuzzy matching
+	1 0b1 enable fuzzy match on z<->zh, c<->ch, s<->sh
+	2 0b10 enable fuzzy match on l<->n
+	flag numbers can be combined with bit or.
+    -->
+    <property name="FuzzyFlag" type="u" access="readwrite"></property>
+
     <!--
 	GetCandidates:
 
diff --git a/main.c b/main.c
index 137b580..5bce0d7 100644
--- a/main.c
+++ b/main.c
@@ -41,11 +41,11 @@ on_handle_get_candidates(ZeroPinyinService *object,
 	GVariantBuilder *candidates_pinyin_indices = NULL;
 
 	/* test data */
-	/* get_candidates_test (preedit_str, fetch_size, candidates_builder, matched_lengths_builder); */
+	/* get_candidates_test(preedit_str, fetch_size, candidates_builder, matched_lengths_builder); */
 	candidates_builder = g_variant_builder_new(G_VARIANT_TYPE("as"));
 	matched_lengths_builder = g_variant_builder_new(G_VARIANT_TYPE("au"));
 	candidates_pinyin_indices = g_variant_builder_new(G_VARIANT_TYPE("aa(ii)"));
-	get_candidates(appdata->db, preedit_str, fetch_size, candidates_builder, matched_lengths_builder, candidates_pinyin_indices);
+	get_candidates(appdata->db, preedit_str, fetch_size, zero_pinyin_service_get_fuzzy_flag(object), candidates_builder, matched_lengths_builder, candidates_pinyin_indices);
 
 	result = g_variant_new("(asauaa(ii))", candidates_builder, matched_lengths_builder, candidates_pinyin_indices);
 	g_assert_nonnull(result);
diff --git a/meson.build b/meson.build
index 3b84d87..7dacfab 100644
--- a/meson.build
+++ b/meson.build
@@ -1,6 +1,6 @@
 # -*- mode: conf -*-
 project('zero-pinyin-service', ['c', 'cpp'],
-  version: '0.8.0',
+  version: '0.9.0',
   license: 'GPL',
   default_options: [
     'warning_level=2',
@@ -44,7 +44,7 @@ shared_dep = [glib, gio, uuid, sqlite3]
 gen_inc = include_directories('.')
 
 gdbus_codegen = find_program('gdbus-codegen')
-zero_pinyin_generated = custom_target('zero-panel-generated',
+zero_pinyin_generated = custom_target('zero-pinyin-generated',
   input: 'com.emacsos.zero.ZeroPinyinService1.ZeroPinyinServiceInterface.xml',
   output: ['zero-pinyin-service-generated.h', 'zero-pinyin-service-generated.c'],
   command: [gdbus_codegen, '--generate-c-code', 'zero-pinyin-service-generated', '@INPUT@'])
diff --git a/operational b/operational
index dc79827..5c69084 100644
--- a/operational
+++ b/operational
@@ -1,6 +1,6 @@
 * COMMENT -*- mode: org -*-
 #+Date: 2019-04-05
-Time-stamp: <2019-10-22>
+Time-stamp: <2019-10-23>
 #+STARTUP: content
 * notes                                                               :entry:
 ** 2019-08-31 ibus-pinyin userdb inference notice.
@@ -52,6 +52,7 @@ shared between zero-pinyin and ibus-pinyin.
 * later                                                               :entry:
 * current                                                             :entry:
 ** 
+** 2019-10-23 bug: type "zhey" doesn't show 这样 candidate.
 ** 2019-10-22 handle a an o en etc differently. only match exactly the character.
 no fuzzy matching or incomplete pinyin matching.
 
@@ -97,6 +98,99 @@ see ~/c/gtk-im-module/, it uses myastyle-pre-commit-check in git pre-commit
 - make the method work. use gobject property maybe.
 - set default flags to my flags. reflect this in UI/config file.
 * done                                                                :entry:
+** 2019-10-22 support fuzzy pinyin.
+- 0 no fuzzy
+- 1 (0b1)
+  z <-> zh
+  c <-> ch
+  s <-> sh
+- 2 (0b10)
+  l <-> n
+- I won't implement other flags at this time.
+- default is no fuzzy.
+- test case:
+  ru chi 如此
+  ci di 此地
+  e nuo 婀娜
+  e luo
+  ci yu 词语
+  song 宋
+  shong
+
+- implementation
+  - WONTFIX add a property in appdata.
+    use a guint flag.
+    only support 0b0 and 0b10 for now.
+
+    Not necessary.
+  - DONE add dbus interface to allow change the property at run time.
+    property is added in dbus interface directly.
+    app just read the property there. there is no network round trip.
+    data is stored in the dbus service server side. not in dbus daemon.
+  - DONE add flags in zero-el.
+    this flag is NOT buffer local.
+    (setq zero-pinyin-fuzzy-flag 3)
+    it will set fuzzy mode when zero-pinyin-reset or zero-pinyin-init.
+    (zero-pinyin-service-set-fuzzy-flag 3)
+    it works.
+- problems
+  - can I make this change backward compatible?
+
+    TODO what will happen when zero asks dbus to set FuzzyFlag property, if
+    running an old zero-pinyin-service?
+  - property generated code is okay.
+  - how to access that property in zero-pinyin-service.c?
+    guint zero_pinyin_service_get_fuzzy_flag (ZeroPinyinService *object);
+
+    this is not the right way.
+    because flag doesn't change much.
+    should query once at start up, then listen to change event and update
+    in-ram data. do not query dbus every time FuzzyFlag is needed.
+
+    WONTFIX add event handler to update appdata->fuzzy_flag when property is
+    changed.  // generated code handle set event and update g_object data in
+    RAM automatically.
+
+    signal org.freedesktop.DBus.Properties.PropertiesChanged
+
+    see example in
+    https://developer.gnome.org/gio/2.26/GDBusProxy.html
+
+  - how to set the property in zero-el?
+    call some dbus built-in service.
+
+    (zero-pinyin-service-quit)
+    run zero-pinyin-service in console
+    (dbus-set-property :session "com.emacsos.zero.ZeroPinyinService1"
+       "/com/emacsos/zero/ZeroPinyinService1"
+       "com.emacsos.zero.ZeroPinyinService1.ZeroPinyinServiceInterface"
+       "FuzzyFlag" 3)
+    (dbus-set-property :session "com.emacsos.zero.ZeroPinyinService1"
+       "/com/emacsos/zero/ZeroPinyinService1"
+       "com.emacsos.zero.ZeroPinyinService1.ZeroPinyinServiceInterface"
+       "FuzzyFlag" 0)
+
+    I think generated code will handle set/get call.
+    maybe just always get the value from
+    zero_pinyin_service_get_fuzzy_flag(ZeroPinyinService *object)
+
+    https://developer.gnome.org/gio/2.60/gdbus-codegen.html
+    Server-side usage
+    just use g_object_get() in server side. it will not talk to dbus.
+    property change should be handled by generated code.
+
+  - set property from emacs and read property in zero-pinyin-service.c
+    works. but the fuzzy SQL logic is not working.
+
+    when set to 3, shong can't produce 宋.
+
+    enabled debug log.
+    I see the problem.
+    shong is not a valid py if fuzzy flag is not used during parsing.
+
+    use correct parsing flag from FuzzyFlag when parsing.
+  - now it works.
+
 ** 2019-08-31 choose maindb like my patched libpyzy.
 - here is patched libpyzy maindb logic:
   files.push_back (m_user_data_dir + "/main.db");
diff --git a/pinyin-id.h b/pinyin-id.h
new file mode 100644
index 0000000..f7e4b5b
--- /dev/null
+++ b/pinyin-id.h
@@ -0,0 +1,76 @@
+#ifndef _PINYIN_ID_H_
+#define _PINYIN_ID_H_
+
+#ifdef __cplusplus
+extern "C"
+{
+#endif
+
+/* data from ../Types.h, copied here so it can be used in C code. */
+
+#define PINYIN_ID_VOID  (-1)
+#define PINYIN_ID_ZERO  (0)
+#define PINYIN_ID_B     (1)
+#define PINYIN_ID_C     (2)
+#define PINYIN_ID_CH    (3)
+#define PINYIN_ID_D     (4)
+#define PINYIN_ID_F     (5)
+#define PINYIN_ID_G     (6)
+#define PINYIN_ID_H     (7)
+#define PINYIN_ID_J     (8)
+#define PINYIN_ID_K     (9)
+#define PINYIN_ID_L     (10)
+#define PINYIN_ID_M     (11)
+#define PINYIN_ID_N     (12)
+#define PINYIN_ID_P     (13)
+#define PINYIN_ID_Q     (14)
+#define PINYIN_ID_R     (15)
+#define PINYIN_ID_S     (16)
+#define PINYIN_ID_SH    (17)
+#define PINYIN_ID_T     (18)
+#define PINYIN_ID_W     (19)
+#define PINYIN_ID_X     (20)
+#define PINYIN_ID_Y     (21)
+#define PINYIN_ID_Z     (22)
+#define PINYIN_ID_ZH    (23)
+#define PINYIN_ID_A     (24)
+#define PINYIN_ID_AI    (25)
+#define PINYIN_ID_AN    (26)
+#define PINYIN_ID_ANG   (27)
+#define PINYIN_ID_AO    (28)
+#define PINYIN_ID_E     (29)
+#define PINYIN_ID_EI    (30)
+#define PINYIN_ID_EN    (31)
+#define PINYIN_ID_ENG   (32)
+#define PINYIN_ID_ER    (33)
+#define PINYIN_ID_I     (34)
+#define PINYIN_ID_IA    (35)
+#define PINYIN_ID_IAN   (36)
+#define PINYIN_ID_IANG  (37)
+#define PINYIN_ID_IAO   (38)
+#define PINYIN_ID_IE    (39)
+#define PINYIN_ID_IN    (40)
+#define PINYIN_ID_ING   (41)
+#define PINYIN_ID_IONG  (42)
+#define PINYIN_ID_IU    (43)
+#define PINYIN_ID_O     (44)
+#define PINYIN_ID_ONG   (45)
+#define PINYIN_ID_OU    (46)
+#define PINYIN_ID_U     (47)
+#define PINYIN_ID_UA    (48)
+#define PINYIN_ID_UAI   (49)
+#define PINYIN_ID_UAN   (50)
+#define PINYIN_ID_UANG  (51)
+#define PINYIN_ID_UE    (52)
+#define PINYIN_ID_VE    PINYIN_ID_UE
+#define PINYIN_ID_UI    (53)
+#define PINYIN_ID_UN    (54)
+#define PINYIN_ID_UO    (55)
+#define PINYIN_ID_V     (56)
+#define PINYIN_ID_NG    PINYIN_ID_VOID
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _PINYIN_ID_H_ */
diff --git a/zero-pinyin-service.c b/zero-pinyin-service.c
index ecd5fc7..ebc5c18 100644
--- a/zero-pinyin-service.c
+++ b/zero-pinyin-service.c
@@ -1,6 +1,7 @@
 #include "zero-pinyin-service.h"
 #include "parse-pinyin.h"
 #include "../sqlite3_util.h"
+#include "pinyin-id.h"
 
 void
 get_candidates_test(const char *preedit_str,
@@ -32,41 +33,89 @@ get_candidates_test(const char *preedit_str,
 	}
 }
 
+/**
+ * get pinyin's fuzzy pair.
+ * for example, zh for z.
+ */
+gint
+get_fuzzy_pair(gint pinyin_id)
+{
+	switch (pinyin_id) {
+	case PINYIN_ID_Z: return PINYIN_ID_ZH;
+	case PINYIN_ID_ZH: return PINYIN_ID_Z;
+	case PINYIN_ID_C: return PINYIN_ID_CH;
+	case PINYIN_ID_CH: return PINYIN_ID_C;
+	case PINYIN_ID_S: return PINYIN_ID_SH;
+	case PINYIN_ID_SH: return PINYIN_ID_S;
+	case PINYIN_ID_L: return PINYIN_ID_N;
+	case PINYIN_ID_N: return PINYIN_ID_L;
+	default:
+		g_assert_not_reached();
+		return pinyin_id;
+	}
+}
+
 /**
  * build where clause for build_sql_for_n_pinyin().
  *
  * @pylist: the pinyin list.
+ * @fuzzy_flag: see dbus interface FuzzyFlag property.
  * @n: number of Pinyin to use in pylist.
  *
  * returns: where_clause, caller should g_free() result after use.
  */
 static char *
 build_where_clause(GList *pylist,
+		   const guint fuzzy_flag,
 		   const guint n)
 {
 	GString *s = NULL;
 	GList *iter = pylist;
-	gboolean first_condition_done = FALSE;
 	Pinyin *thispy = NULL;
+
 	s = g_string_new(NULL);
+	/* allow append "AND something" without checking */
+	g_string_append_printf(s, "1=1 ");
 	for (guint i = 0; i < n; ++i) {
 		g_assert_nonnull(iter);
 		thispy = (Pinyin *) iter->data;
 		/* do not allow omit shengmu. always do strict match */
-		if (G_LIKELY(first_condition_done)) {
+		switch (thispy->shengmu_i) {
+		case PINYIN_ID_Z:
+		case PINYIN_ID_C:
+		case PINYIN_ID_S:
+		case PINYIN_ID_ZH:
+		case PINYIN_ID_CH:
+		case PINYIN_ID_SH:
+			if (fuzzy_flag & FUZZY_FLAG_ZCS_ZHCHSH) {
+				g_string_append_printf(
+					s,
+					"AND (s%u=%d OR s%u=%d) ",
+					i, thispy->shengmu_i,
+					i, get_fuzzy_pair(thispy->shengmu_i));
+			} else {
+				goto NO_FUZZY;
+			}
+			break;
+		case PINYIN_ID_L:
+		case PINYIN_ID_N:
+			if (fuzzy_flag & FUZZY_FLAG_L_N) {
+				g_string_append_printf(
+					s,
+					"AND (s%u=%d OR s%u=%d) ",
+					i, thispy->shengmu_i,
+					i, get_fuzzy_pair(thispy->shengmu_i));
+			} else {
+				goto NO_FUZZY;
+			}
+			break;
+		default:
+		NO_FUZZY:
 			g_string_append_printf(s, "AND s%u=%d ", i, thispy->shengmu_i);
-		} else {
-			g_string_append_printf(s, "s%u=%d ", i, thispy->shengmu_i);
-			first_condition_done = TRUE;
 		}
 		/* allow omit yunmu, if 0 don't match on it */
 		if (thispy->yunmu_i) {
-			if (G_LIKELY(first_condition_done)) {
-				g_string_append_printf(s, "AND y%u=%d ", i, thispy->yunmu_i);
-			} else {
-				g_string_append_printf(s, "y%u=%d ", i, thispy->yunmu_i);
-				first_condition_done = TRUE;
-			}
+			g_string_append_printf(s, "AND y%u=%d ", i, thispy->yunmu_i);
 		}
 		iter = iter->next;
 	}
@@ -103,6 +152,7 @@ build_s_y_fields(const guint n)
  */
 static char *
 build_sql_for_n_pinyin(GList *pylist,
+		       const guint fuzzy_flag,
 		       const guint n,
 		       const guint limit)
 {
@@ -119,7 +169,7 @@ build_sql_for_n_pinyin(GList *pylist,
 	g_string_append_printf(sql, s_y_fields);
 	g_string_append_printf(
 		sql, "FROM maindb.py_phrase_%u WHERE ", n - 1);
-	where_clause = build_where_clause(pylist, n);
+	where_clause = build_where_clause(pylist, fuzzy_flag, n);
 	g_assert_nonnull(where_clause);
 	g_debug("where_clause=%s", where_clause);
 	sql = g_string_append(sql, where_clause);
@@ -182,6 +232,7 @@ get_matched_py_length(const char *preedit_str,
  * @preedit_str: the pinyin preedit str. can contain '. This is needed to
  *               calculate matched_py_length.
  * @pylist: the pinyin list.
+ * @fuzzy_flag: see dbus interface FuzzyFlag property.
  * @group_size: the fixed word length. use this many pinyin from pinyin list.
  * @limit: fetch this many result is enough for user. more is not a problem though.
  * @candidates: the result candidate list. caller should free this after use.
@@ -192,6 +243,7 @@ static guint
 get_candidates_for_n_pinyin(sqlite3 *db,
 			    const char *preedit_str,
 			    GList *pylist,
+			    const guint fuzzy_flag,
 			    const guint group_size,
 			    const guint limit,
 			    GList **candidates)
@@ -207,7 +259,8 @@ get_candidates_for_n_pinyin(sqlite3 *db,
 	gint r = 0;
 	/* build SQL and run SQL query */
 	char *sql = NULL;
-	sql = build_sql_for_n_pinyin(pylist, group_size, MAX(limit, DEFAULT_LIMIT));
+	sql = build_sql_for_n_pinyin(pylist, fuzzy_flag,
+				     group_size, MAX(limit, DEFAULT_LIMIT));
 	g_debug("build_sql_for_n_pinyin result SQL:\n\n%s\n", sql);
 
 	guint matched_py_length = get_matched_py_length(preedit_str, pylist, group_size);
@@ -296,10 +349,31 @@ add_candidate_to_builders(Candidate *c,
 	g_free(c->py_indices);
 }
 
+/**
+ * convert zero FuzzyFlag to libpyzy flag.
+ * I don't use libpyzy flag directly because it is overly complex.
+ */
+guint
+to_pyzy_flag(const guint fuzzy_flag)
+{
+	guint result = 0;
+	if (fuzzy_flag & FUZZY_FLAG_ZCS_ZHCHSH) {
+		result = result |
+			PINYIN_FUZZY_Z_ZH | PINYIN_FUZZY_ZH_Z |
+			PINYIN_FUZZY_C_CH | PINYIN_FUZZY_CH_C |
+			PINYIN_FUZZY_S_SH | PINYIN_FUZZY_SH_S;
+	}
+	if (fuzzy_flag & FUZZY_FLAG_L_N) {
+		result = result | PINYIN_FUZZY_L_N | PINYIN_FUZZY_N_L;
+	}
+	return result;
+}
+
 void
 get_candidates(sqlite3 *db,
 	       const char *preedit_str,
 	       const guint fetch_size,
+	       const guint fuzzy_flag,
 	       GVariantBuilder *candidates_builder,
 	       GVariantBuilder *matched_lengths_builder,
 	       GVariantBuilder *candidates_pinyin_indices)
@@ -310,7 +384,8 @@ get_candidates(sqlite3 *db,
 	}
 	GList *pylist = NULL;
 	guint pylist_len = 0;
-	pylist = parse_pinyin(preedit_str, 15, PINYIN_FLAGS_NONE);
+	g_debug("fuzzy_flag=%u", fuzzy_flag);
+	pylist = parse_pinyin(preedit_str, 15, to_pyzy_flag(fuzzy_flag));
 	pylist_len = g_list_length(pylist);
 
 	guint group_size = pylist_len;
@@ -319,7 +394,7 @@ get_candidates(sqlite3 *db,
 	GList *candidates = NULL;
 	while (fetched_size < fetch_size && group_size > 0) {
 		g_info("phrase length=%u", group_size);
-		r = get_candidates_for_n_pinyin(db, preedit_str, pylist, group_size, fetch_size - fetched_size, &candidates);
+		r = get_candidates_for_n_pinyin(db, preedit_str, pylist, fuzzy_flag, group_size, fetch_size - fetched_size, &candidates);
 		if (candidates) {
 			GList *iter = g_list_first(candidates);
 			Candidate *c = NULL;
diff --git a/zero-pinyin-service.h b/zero-pinyin-service.h
index 2067e52..75bafc6 100644
--- a/zero-pinyin-service.h
+++ b/zero-pinyin-service.h
@@ -11,6 +11,11 @@ G_BEGIN_DECLS
 #define ZERO_PINYIN_OBJECT_PATH "/com/emacsos/zero/ZeroPinyinService1"
 #define ZERO_PINYIN_INTERFACE_NAME "com.emacsos.zero.ZeroPinyinService1.ZeroPinyinServiceInterface"
 
+static const guint FUZZY_FLAG_NONE = 0;
+static const guint FUZZY_FLAG_ZCS_ZHCHSH = 1;
+static const guint FUZZY_FLAG_L_N = 2;
+/* Note: next flag should be 4, always use a new bit for flag. */
+
 typedef struct {
 	gint shengmu_i;
 	gint yunmu_i;
@@ -45,6 +50,7 @@ void get_candidates_test(const char *preedit_str,
 void get_candidates(sqlite3 *db,
 		    const char *preedit_str,
 		    const guint fetch_size,
+		    const guint fuzzy_flag,
 		    GVariantBuilder *candidates_builder,
 		    GVariantBuilder *matched_lengths_builder,
 		    GVariantBuilder *candidates_pinyin_indices);
-- 
GitLab