Fredrik Lundh: here's the 96.6% version of SRE

1 files changed, 68 insertions, 27 deletions

diff --git a/Lib/sre_constants.py b/Lib/sre_constants.py
index af883094d4..531dc319cb 100644
--- a/Lib/sre_constants.py
+++ b/Lib/sre_constants.py
@@ -48,20 +48,31 @@ SUBPATTERN = "subpattern"
 
 # positions
 AT_BEGINNING = "at_beginning"
+AT_BEGINNING_LINE = "at_beginning_line"
 AT_BOUNDARY = "at_boundary"
 AT_NON_BOUNDARY = "at_non_boundary"
 AT_END = "at_end"
+AT_END_LINE = "at_end_line"
 
 # categories
-
 CATEGORY_DIGIT = "category_digit"
 CATEGORY_NOT_DIGIT = "category_not_digit"
 CATEGORY_SPACE = "category_space"
 CATEGORY_NOT_SPACE = "category_not_space"
 CATEGORY_WORD = "category_word"
 CATEGORY_NOT_WORD = "category_not_word"
+CATEGORY_LINEBREAK = "category_linebreak"
+CATEGORY_NOT_LINEBREAK = "category_not_linebreak"
+CATEGORY_LOC_DIGIT = "category_loc_digit"
+CATEGORY_LOC_NOT_DIGIT = "category_loc_not_digit"
+CATEGORY_LOC_SPACE = "category_loc_space"
+CATEGORY_LOC_NOT_SPACE = "category_loc_not_space"
+CATEGORY_LOC_WORD = "category_loc_word"
+CATEGORY_LOC_NOT_WORD = "category_loc_not_word"
+CATEGORY_LOC_LINEBREAK = "category_loc_linebreak"
+CATEGORY_LOC_NOT_LINEBREAK = "category_loc_not_linebreak"
 
-CODES = [
+OPCODES = [
 
     # failure=0 success=1 (just because it looks better that way :-)
     FAILURE, SUCCESS,
@@ -87,45 +98,75 @@ CODES = [
 
 ]
 
-# convert to dictionary
-c = {}
-i = 0
-for code in CODES:
-    c[code] = i
-    i = i + 1
-CODES = c
+ATCODES = [
+    AT_BEGINNING, AT_BEGINNING_LINE, AT_BOUNDARY,
+    AT_NON_BOUNDARY, AT_END, AT_END_LINE
+]
+
+CHCODES = [
+    CATEGORY_DIGIT, CATEGORY_NOT_DIGIT, CATEGORY_SPACE,
+    CATEGORY_NOT_SPACE, CATEGORY_WORD, CATEGORY_NOT_WORD,
+    CATEGORY_LINEBREAK, CATEGORY_NOT_LINEBREAK, CATEGORY_LOC_DIGIT,
+    CATEGORY_LOC_NOT_DIGIT, CATEGORY_LOC_SPACE,
+    CATEGORY_LOC_NOT_SPACE, CATEGORY_LOC_WORD, CATEGORY_LOC_NOT_WORD,
+    CATEGORY_LOC_LINEBREAK, CATEGORY_LOC_NOT_LINEBREAK
+]
+
+def makedict(list):
+    d = {}
+    i = 0
+    for item in list:
+	d[item] = i
+	i = i + 1
+    return d
+
+OPCODES = makedict(OPCODES)
+ATCODES = makedict(ATCODES)
+CHCODES = makedict(CHCODES)
 
 # replacement operations for "ignore case" mode
-MAP_IGNORE = {
+OP_IGNORE = {
     GROUP: GROUP_IGNORE,
     IN: IN_IGNORE,
     LITERAL: LITERAL_IGNORE,
     NOT_LITERAL: NOT_LITERAL_IGNORE
 }
 
-POSITIONS = {
-    AT_BEGINNING: ord("a"),
-    AT_BOUNDARY: ord("b"),
-    AT_NON_BOUNDARY: ord("B"),
-    AT_END: ord("z"),
+AT_MULTILINE = {
+    AT_BEGINNING: AT_BEGINNING_LINE,
+    AT_END: AT_END_LINE
 }
 
-CATEGORIES = {
-    CATEGORY_DIGIT: ord("d"),
-    CATEGORY_NOT_DIGIT: ord("D"),
-    CATEGORY_SPACE: ord("s"),
-    CATEGORY_NOT_SPACE: ord("S"),
-    CATEGORY_WORD: ord("w"),
-    CATEGORY_NOT_WORD: ord("W"),
+CH_LOCALE = {
+    CATEGORY_DIGIT: CATEGORY_LOC_DIGIT,
+    CATEGORY_NOT_DIGIT: CATEGORY_LOC_NOT_DIGIT,
+    CATEGORY_SPACE: CATEGORY_LOC_SPACE,
+    CATEGORY_NOT_SPACE: CATEGORY_LOC_NOT_SPACE,
+    CATEGORY_WORD: CATEGORY_LOC_WORD,
+    CATEGORY_NOT_WORD: CATEGORY_LOC_NOT_WORD,
+    CATEGORY_LINEBREAK: CATEGORY_LOC_LINEBREAK,
+    CATEGORY_NOT_LINEBREAK: CATEGORY_LOC_NOT_LINEBREAK
 }
 
+# flags
+SRE_FLAG_TEMPLATE = 1 # NYI
+SRE_FLAG_IGNORECASE = 2
+SRE_FLAG_LOCALE = 4
+SRE_FLAG_MULTILINE = 8
+SRE_FLAG_DOTALL = 16
+SRE_FLAG_VERBOSE = 32
+
 if __name__ == "__main__":
     import string
-    items = CODES.items()
-    items.sort(lambda a, b: cmp(a[1], b[1]))
+    def dump(f, d, prefix):
+	items = d.items()
+	items.sort(lambda a, b: cmp(a[1], b[1]))
+	for k, v in items:
+	    f.write("#define %s_%s %s\n" % (prefix, string.upper(k), v))
     f = open("sre_constants.h", "w")
-    f.write("/* generated by sre_constants.py */\n")
-    for k, v in items:
-	f.write("#define SRE_OP_" + string.upper(k) + " " + str(v) + "\n")
+    f.write("/* generated from sre_constants.py */\n")
+    dump(f, OPCODES, "SRE_OP")
+    dump(f, ATCODES, "SRE")
+    dump(f, CHCODES, "SRE")
     f.close()
     print "done"