From bd0a7f68729c7c68a0d607237d0e7cd256f22f52 Mon Sep 17 00:00:00 2001
From: Yuanle Song <sylecn@gmail.com>
Date: Mon, 8 Apr 2019 11:06:19 +0800
Subject: [PATCH] v0.5.1 support pinyin with ' in them.

now xi'an etc types okay.
---
 meson.build           |  2 +-
 zero-pinyin-service.c | 45 ++++++++++++++++++++++++++++++++++++-------
 2 files changed, 39 insertions(+), 8 deletions(-)

diff --git a/meson.build b/meson.build
index a0e565d..8defd75 100644
--- a/meson.build
+++ b/meson.build
@@ -1,6 +1,6 @@
 # -*- mode: conf -*-
 project('zero-pinyin-service', ['c', 'cpp'],
-  version: '0.5.0',
+  version: '0.5.1',
   license: 'GPL',
   default_options: [
     'warning_level=2',
diff --git a/zero-pinyin-service.c b/zero-pinyin-service.c
index 5f993a8..3796102 100644
--- a/zero-pinyin-service.c
+++ b/zero-pinyin-service.c
@@ -112,9 +112,44 @@ build_sql_for_n_pinyin (GList* pylist,
 	return result;
 }
 
+/**
+ * For a candidate of length group_size, calculate the matched py length.
+ *
+ * This is part of get_candidates_for_n_pinyin().
+ *
+ * see param meaning there.
+ */
+static guint
+get_matched_py_length (const char* preedit_str,
+		       GList* pylist,
+		       const guint group_size)
+{
+	guint matched_py_length = 0;
+	GList* iter = pylist;
+
+	g_assert_cmpint (group_size, >=, 1);
+	/* For usual pinyin string, just add up the Pinyin length. But for
+	 * pinyin that contains ', when a Pinyin in pylist is used, also take
+	 * the ' before and after it. */
+	for (guint i = 0; i < group_size; ++i) {
+		while (preedit_str[matched_py_length] == '\'') {
+			matched_py_length++;
+		}
+		matched_py_length += ((Pinyin*) iter->data)->length;
+		while (preedit_str[matched_py_length] == '\'') {
+			matched_py_length++;
+		}
+		iter = iter->next;
+	}
+	return matched_py_length;
+}
+
 /**
  * fetch candidates for a fixed word length.
  *
+ * @db: sqlite3 db handler.
+ * @preedit_str: the pinyin preedit str. can contain '. This is needed to
+ *               calculate matched_py_length.
  * @pylist: the pinyin list.
  * @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.
@@ -124,6 +159,7 @@ build_sql_for_n_pinyin (GList* pylist,
  */
 static guint
 get_candidates_for_n_pinyin (sqlite3* db,
+			     const char* preedit_str,
 			     GList* pylist,
 			     const guint group_size,
 			     const guint limit,
@@ -143,12 +179,7 @@ get_candidates_for_n_pinyin (sqlite3* db,
 	sql = build_sql_for_n_pinyin (pylist, group_size, MAX (limit, DEFAULT_LIMIT));
 	g_message ("build_sql_for_n_pinyin result SQL:\n\n%s\n", sql);
 
-	guint matched_py_length = 0;
-	GList* iter = pylist;
-	for (guint i = 0; i < group_size; ++i) {
-		matched_py_length += ((Pinyin*) iter->data)->length;
-		iter = iter->next;
-	}
+	guint matched_py_length = get_matched_py_length (preedit_str, pylist, group_size);
 
 	sqlite3_stmt* stmt = NULL;
 	const char* unused;
@@ -221,7 +252,7 @@ get_candidates (sqlite3* db,
 	GList* candidates = NULL;
 	while (fetched_size < fetch_size && group_size > 0) {
 		g_message ("phrase length=%u", group_size);
-		r = get_candidates_for_n_pinyin (db, pylist, group_size, fetch_size - fetched_size, &candidates);
+		r = get_candidates_for_n_pinyin (db, preedit_str, pylist, group_size, fetch_size - fetched_size, &candidates);
 		if (candidates) {
 			GList* iter = g_list_first (candidates);
 			Candidate* c = NULL;
-- 
GitLab