Mercurial > cpython-lru_cache-weakref

diff Objects/unicodeobject.c @ 15749:77c761cd1272 legacy-trunk

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
This patch adds a new feature to the builtin charmap codec: The mapping dictionaries can now contain 1-n mappings, meaning that character ordinals may be mapped to strings or Unicode object, e.g. 0x0078 ('x') -> u"abc", causing the ordinal to be replaced by the complete string or Unicode object instead of just one character. Another feature introduced by the patch is that of mapping oridnals to the emtpy string. This allows removing characters. The patch is different from patch #103100 in that it does not cause a performance hit for the normal use case of 1-1 mappings. Written by Marc-Andre Lemburg, copyright assigned to Guido van Rossum.
author Marc-André Lemburg <mal@egenix.com>
date Sat, 06 Jan 2001 14:59:58 +0000
parents bf9bb0e3dd34
children f7f3be3d00b9
line wrap: on
line diff
--- a/Objects/unicodeobject.c	Fri Jan 05 20:54:07 2001 +0000
+++ b/Objects/unicodeobject.c	Sat Jan 06 14:59:58 2001 +0000
@@ -1947,6 +1947,7 @@
 {
     PyUnicodeObject *v;
     Py_UNICODE *p;
+    int extrachars = 0;
     
     /* Default to Latin-1 */
     if (mapping == NULL)
@@ -1998,14 +1999,33 @@
 	    }
 	}
 	else if (PyUnicode_Check(x)) {
-	    if (PyUnicode_GET_SIZE(x) != 1) {
+	    int targetsize = PyUnicode_GET_SIZE(x);
+
+	    if (targetsize == 1)
+		/* 1-1 mapping */
+		*p++ = *PyUnicode_AS_UNICODE(x);
+
+	    else if (targetsize > 1) {
 		/* 1-n mapping */
-		PyErr_SetString(PyExc_NotImplementedError,
-				"1-n mappings are currently not implemented");
+		if (targetsize > extrachars) {
+		    /* resize first */
+		    int oldpos = (int)(p - PyUnicode_AS_UNICODE(v));
+		    int needed = (targetsize - extrachars) + \
+			         (targetsize << 2);
+		    extrachars += needed;
+		    if (_PyUnicode_Resize(v, PyUnicode_GET_SIZE(v) + needed)) {
 		Py_DECREF(x);
 		goto onError;
 	    }
-	    *p++ = *PyUnicode_AS_UNICODE(x);
+		    p = PyUnicode_AS_UNICODE(v) + oldpos;
+		}
+		Py_UNICODE_COPY(p,
+				PyUnicode_AS_UNICODE(x),
+				targetsize);
+		p += targetsize;
+		extrachars -= targetsize;
+	    }
+	    /* 1-0 mapping: skip the character */
 	}
 	else {
 	    /* wrong return value */
@@ -2063,6 +2083,7 @@
 {
     PyObject *v;
     char *s;
+    int extrachars = 0;
 
     /* Default to Latin-1 */
     if (mapping == NULL)
@@ -2114,14 +2135,33 @@
 	    }
 	}
 	else if (PyString_Check(x)) {
-	    if (PyString_GET_SIZE(x) != 1) {
+	    int targetsize = PyString_GET_SIZE(x);
+
+	    if (targetsize == 1)
+		/* 1-1 mapping */
+		*s++ = *PyString_AS_STRING(x);
+
+	    else if (targetsize > 1) {
 		/* 1-n mapping */
-		PyErr_SetString(PyExc_NotImplementedError,
-		      "1-n mappings are currently not implemented");
+		if (targetsize > extrachars) {
+		    /* resize first */
+		    int oldpos = (int)(s - PyString_AS_STRING(v));
+		    int needed = (targetsize - extrachars) + \
+			         (targetsize << 2);
+		    extrachars += needed;
+		    if (_PyString_Resize(&v, PyString_GET_SIZE(v) + needed)) {
 		Py_DECREF(x);
 		goto onError;
 	    }
-	    *s++ = *PyString_AS_STRING(x);
+		    s = PyString_AS_STRING(v) + oldpos;
+		}
+		memcpy(s,
+		       PyString_AS_STRING(x),
+		       targetsize);
+		s += targetsize;
+		extrachars -= targetsize;
+	    }
+	    /* 1-0 mapping: skip the character */
 	}
 	else {
 	    /* wrong return value */