summaryrefslogtreecommitdiffstats
path: root/Parser
diff options
context:
space:
mode:
authorThomas Wouters <thomas@python.org>2000-08-24 20:11:32 (GMT)
committerThomas Wouters <thomas@python.org>2000-08-24 20:11:32 (GMT)
commit434d0828d81855692d45c3fdc0905a67c17d83ba (patch)
treefb920985e81a5c4091f75800ebdea7ed33a657e0 /Parser
parentdd8dbdb7172fbafb5ffab8600e620103fc19879e (diff)
downloadcpython-434d0828d81855692d45c3fdc0905a67c17d83ba.zip
cpython-434d0828d81855692d45c3fdc0905a67c17d83ba.tar.gz
cpython-434d0828d81855692d45c3fdc0905a67c17d83ba.tar.bz2
Support for three-token characters (**=, >>=, <<=) which was written by
Michael Hudson, and support in general for the augmented assignment syntax. The graminit.c patch is large!
Diffstat (limited to 'Parser')
-rw-r--r--Parser/grammar.c12
-rw-r--r--Parser/tokenizer.c94
2 files changed, 106 insertions, 0 deletions
diff --git a/Parser/grammar.c b/Parser/grammar.c
index 07e59ff..c4efce7 100644
--- a/Parser/grammar.c
+++ b/Parser/grammar.c
@@ -211,6 +211,18 @@ translabel(grammar *g, label *lb)
printf("Unknown OP label %s\n",
lb->lb_str);
}
+ else if (lb->lb_str[2] && lb->lb_str[3] && lb->lb_str[4] == lb->lb_str[0]) {
+ int type = (int) PyToken_ThreeChars(lb->lb_str[1],
+ lb->lb_str[2],
+ lb->lb_str[3]);
+ if (type != OP) {
+ lb->lb_type = type;
+ lb->lb_str = NULL;
+ }
+ else
+ printf("Unknown OP label %s\n",
+ lb->lb_str);
+ }
else
printf("Can't translate STRING label %s\n",
lb->lb_str);
diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c
index 160f6ba..eb84d14 100644
--- a/Parser/tokenizer.c
+++ b/Parser/tokenizer.c
@@ -78,6 +78,17 @@ char *_PyParser_TokenNames[] = {
"LEFTSHIFT",
"RIGHTSHIFT",
"DOUBLESTAR",
+ "PLUSEQUAL",
+ "MINEQUAL",
+ "STAREQUAL",
+ "SLASHEQUAL",
+ "PERCENTEQUAL",
+ "AMPEREQUAL",
+ "VBAREQUAL",
+ "CIRCUMFLEXEQUAL",
+ "LEFTSHIFTEQUAL",
+ "RIGHTSHIFTEQUAL",
+ "DOUBLESTAREQUAL",
/* This table must match the #defines in token.h! */
"OP",
"<ERRORTOKEN>",
@@ -388,15 +399,91 @@ PyToken_TwoChars(int c1, int c2)
case '>': return RIGHTSHIFT;
}
break;
+ case '+':
+ switch (c2) {
+ case '=': return PLUSEQUAL;
+ }
+ break;
+ case '-':
+ switch (c2) {
+ case '=': return MINEQUAL;
+ }
+ break;
case '*':
switch (c2) {
case '*': return DOUBLESTAR;
+ case '=': return STAREQUAL;
+ }
+ break;
+ case '/':
+ switch (c2) {
+ case '=': return SLASHEQUAL;
+ }
+ break;
+ case '|':
+ switch (c2) {
+ case '=': return VBAREQUAL;
+ }
+ break;
+ case '%':
+ switch (c2) {
+ case '=': return PERCENTEQUAL;
+ }
+ break;
+ case '&':
+ switch (c2) {
+ case '=': return AMPEREQUAL;
+ }
+ break;
+ case '^':
+ switch (c2) {
+ case '=': return CIRCUMFLEXEQUAL;
}
break;
}
return OP;
}
+int
+PyToken_ThreeChars(int c1, int c2, int c3)
+{
+ switch (c1) {
+ case '<':
+ switch (c2) {
+ case '<':
+ switch (c3) {
+ case '=':
+ return LEFTSHIFTEQUAL;
+ break;
+ }
+ break;
+ }
+ break;
+ case '>':
+ switch (c2) {
+ case '>':
+ switch (c3) {
+ case '=':
+ return RIGHTSHIFTEQUAL;
+ break;
+ }
+ break;
+ }
+ break;
+ case '*':
+ switch (c2) {
+ case '*':
+ switch (c3) {
+ case '=':
+ return DOUBLESTAREQUAL;
+ break;
+ }
+ break;
+ }
+ break;
+ }
+ return OP;
+}
static int
indenterror(struct tok_state *tok)
@@ -770,6 +857,13 @@ PyTokenizer_Get(register struct tok_state *tok, char **p_start,
int c2 = tok_nextc(tok);
int token = PyToken_TwoChars(c, c2);
if (token != OP) {
+ int c3 = tok_nextc(tok);
+ int token3 = PyToken_ThreeChars(c, c2, c3);
+ if (token3 != OP) {
+ token = token3;
+ } else {
+ tok_backup(tok, c3);
+ }
*p_start = tok->start;
*p_end = tok->cur;
return token;