From 86bbc257b00fc2e37f6c80a0c48da6f619fb037a Mon Sep 17 00:00:00 2001
From: "Reece H. Dunn" <msclrhd@gmail.com>
Date: Tue, 24 Jul 2018 22:32:39 +0100
Subject: [PATCH] Support matching any length strings in the replacement rules.

---
 CHANGELOG.md                 |  2 ++
 docs/dictionary.md           | 10 +++++-----
 src/libespeak-ng/translate.c | 20 +++++++++++++++-----
 3 files changed, 22 insertions(+), 10 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 70242c03..7c032270 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -14,6 +14,8 @@ The espeak-ng project is a fork of the espeak project.
    BCP 47 language subtag registry making the newly registered `hyw` language code the
    preferred value for `hy-arevmda`. This change keeps support for detecting the
    `hy-arevela` and `hy-arevmda` language tags.
+*  Support any length replacement rule strings for the source part of the rule (replacing
+   from the 'source' string to the 'target' string).
 *  Add more tests to check the various parts of espeak-ng.
 *  Various changes to clean up the codebase.
 *  Fix various compiler warnings (`-Winitialized`, `-Wmissing-prototypes`, `-Wreturn-type`,
diff --git a/docs/dictionary.md b/docs/dictionary.md
index 2ac9a731..48d79844 100644
--- a/docs/dictionary.md
+++ b/docs/dictionary.md
@@ -509,11 +509,11 @@ each language. The number fragments are given in the `*_list` file.
 ## Character Substitution
 
 Character substitutions can be specified by using a `.replace` section
-at the start of the `*_rules` file. In each line one character can be
-replaced by one or two characters. (Source and target of replacement can consume
-up to four bytes.) This substitution is done to a word _before_ word is searched
-in `*_list` or `*_listx` file and translated using the spelling-to-phoneme rules.
-Only the lower-case version of the characters needs to be specified. e.g.:
+at the start of the `*_rules` file. In each line multiple _source_ characters
+can be replaced by one or two characters. This substitution is done to a word
+_before_ word is searched in `*_list` or `*_listx` file and translated using
+the spelling-to-phoneme rules. Only the lower-case version of the characters
+needs to be specified. e.g.:
 
 	.replace
 	   ô   ő   // (Hungarian) allow the use of o-circumflex instead of o-double-accute
diff --git a/src/libespeak-ng/translate.c b/src/libespeak-ng/translate.c
index a1747c40..eeaa19ea 100644
--- a/src/libespeak-ng/translate.c
+++ b/src/libespeak-ng/translate.c
@@ -1804,12 +1804,22 @@ static const char *FindReplacementChars(Translator *tr, const char **pfrom, unsi
 		if (nc == fc) {
 			if (*from == 0) return from + 1;
 
-			from += utf8_in((int *)&fc, from);
-			match_next += utf8_in((int *)&nc, match_next);
+			bool matched = true;
+			int nmatched = 0;
+			while (*from != 0) {
+				from += utf8_in((int *)&fc, from);
 
-			nc = towlower2(nc, tr);
-			if (*from == 0 && nc == fc) {
-				*ignore_next_n = 1;
+				match_next += utf8_in((int *)&nc, match_next);
+				nc = towlower2(nc, tr);
+
+				if (nc != fc)
+					matched = false;
+				else
+					nmatched++;
+			}
+
+			if (*from == 0 && matched) {
+				*ignore_next_n = nmatched;
 				return from + 1;
 			}
 		}