diff options
Diffstat (limited to 'Lib/sre_compile.py')
| -rw-r--r-- | Lib/sre_compile.py | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/Lib/sre_compile.py b/Lib/sre_compile.py index bd40705..471753e 100644 --- a/Lib/sre_compile.py +++ b/Lib/sre_compile.py @@ -276,10 +276,10 @@ def _mk_bitmap(bits): # set is constructed. Then, this bitmap is sliced into chunks of 256 # characters, duplicate chunks are eliminated, and each chunk is # given a number. In the compiled expression, the charset is -# represented by a 16-bit word sequence, consisting of one word for -# the number of different chunks, a sequence of 256 bytes (128 words) +# represented by a 32-bit word sequence, consisting of one word for +# the number of different chunks, a sequence of 256 bytes (64 words) # of chunk numbers indexed by their original chunk position, and a -# sequence of chunks (16 words each). +# sequence of 256-bit chunks (8 words each). # Compression is normally good: in a typical charset, large ranges of # Unicode will be either completely excluded (e.g. if only cyrillic @@ -294,7 +294,7 @@ def _mk_bitmap(bits): # In UCS-4 mode, the BIGCHARSET opcode still supports only subsets # of the basic multilingual plane; an efficient representation -# for all of UTF-16 has not yet been developed. This means, +# for all of Unicode has not yet been developed. This means, # in particular, that negated charsets cannot be represented as # bigcharsets. |