Turns out Neil didn't intend for *all* of his gen-branch work to get
committed.
tokenize.py: I like these changes, and have tested them extensively
without even realizing it, so I just updated the docstring and the docs.
tabnanny.py: Also liked this, but did a little code fiddling. I should
really rewrite this to *exploit* generators, but that's near the bottom
of my effort/benefit scale so doubt I'll get to it anytime soon (it
would be most useful as a non-trivial example of ideal use of generators;
but test_generators.py has already grown plenty of food-for-thought
examples).
inspect.py: I'm sure Ping intended for this to continue running even
under 1.5.2, so I reverted this to the last pre-gen-branch version. The
"bugfix" I checked in in-between was actually repairing a bug *introduced*
by the conversion to generators, so it's OK that the reverted version
doesn't reflect that checkin.
diff --git a/Lib/inspect.py b/Lib/inspect.py
index eeb54d2..2d88bc1 100644
--- a/Lib/inspect.py
+++ b/Lib/inspect.py
@@ -349,28 +349,32 @@
return self.lines[i]
else: return ''
+class EndOfBlock(Exception): pass
+
+class BlockFinder:
+ """Provide a tokeneater() method to detect the end of a code block."""
+ def __init__(self):
+ self.indent = 0
+ self.started = 0
+ self.last = 0
+
+ def tokeneater(self, type, token, (srow, scol), (erow, ecol), line):
+ if not self.started:
+ if type == tokenize.NAME: self.started = 1
+ elif type == tokenize.NEWLINE:
+ self.last = srow
+ elif type == tokenize.INDENT:
+ self.indent = self.indent + 1
+ elif type == tokenize.DEDENT:
+ self.indent = self.indent - 1
+ if self.indent == 0: raise EndOfBlock, self.last
+
def getblock(lines):
"""Extract the block of code at the top of the given list of lines."""
-
- indent = 0
- started = 0
- last = 0
- tokens = tokenize.generate_tokens(ListReader(lines).readline)
-
- for (type, token, (srow, scol), (erow, ecol), line) in tokens:
- if not started:
- if type == tokenize.NAME:
- started = 1
- elif type == tokenize.NEWLINE:
- last = srow
- elif type == tokenize.INDENT:
- indent = indent + 1
- elif type == tokenize.DEDENT:
- indent = indent - 1
- if indent == 0:
- return lines[:last]
- else:
- raise ValueError, "unable to find block"
+ try:
+ tokenize.tokenize(ListReader(lines).readline, BlockFinder().tokeneater)
+ except EndOfBlock, eob:
+ return lines[:eob.args[0]]
def getsourcelines(object):
"""Return a list of source lines and starting line number for an object.
diff --git a/Lib/tabnanny.py b/Lib/tabnanny.py
index 8323a33..35e5cfa 100755
--- a/Lib/tabnanny.py
+++ b/Lib/tabnanny.py
@@ -14,6 +14,8 @@
import sys
import getopt
import tokenize
+if not hasattr(tokenize, 'NL'):
+ raise ValueError("tokenize.NL doesn't exist -- tokenize module too old")
__all__ = ["check"]
@@ -243,15 +245,11 @@
prefix = prefix + "s"
return prefix + " " + string.join(firsts, ', ')
-# Need Guido's enhancement
-assert hasattr(tokenize, 'NL'), "tokenize module too old"
-
-def process_tokens(tokens,
- INDENT=tokenize.INDENT,
- DEDENT=tokenize.DEDENT,
- NEWLINE=tokenize.NEWLINE,
- JUNK=(tokenize.COMMENT, tokenize.NL)):
-
+def process_tokens(tokens):
+ INDENT = tokenize.INDENT
+ DEDENT = tokenize.DEDENT
+ NEWLINE = tokenize.NEWLINE
+ JUNK = tokenize.COMMENT, tokenize.NL
indents = [Whitespace("")]
check_equal = 0
diff --git a/Lib/tokenize.py b/Lib/tokenize.py
index b3ee4a8..b79cdc0 100644
--- a/Lib/tokenize.py
+++ b/Lib/tokenize.py
@@ -1,13 +1,26 @@
"""Tokenization help for Python programs.
-This module exports a function called 'tokenize()' that breaks a stream of
+generate_tokens(readline) is a generator that breaks a stream of
text into Python tokens. It accepts a readline-like method which is called
-repeatedly to get the next line of input (or "" for EOF) and a "token-eater"
-function which is called once for each token found. The latter function is
-passed the token type, a string containing the token, the starting and
-ending (row, column) coordinates of the token, and the original line. It is
-designed to match the working of the Python tokenizer exactly, except that
-it produces COMMENT tokens for comments and gives type OP for all operators."""
+repeatedly to get the next line of input (or "" for EOF). It generates
+5-tuples with these members:
+
+ the token type (see token.py)
+ the token (a string)
+ the starting (row, column) indices of the token (a 2-tuple of ints)
+ the ending (row, column) indices of the token (a 2-tuple of ints)
+ the original line (string)
+
+It is designed to match the working of the Python tokenizer exactly, except
+that it produces COMMENT tokens for comments and gives type OP for all
+operators
+
+Older entry points
+ tokenize_loop(readline, tokeneater)
+ tokenize(readline, tokeneater=printtoken)
+are the same, except instead of generating tokens, tokeneater is a callback
+function to which the 5 fields described above are passed as 5 arguments,
+each time a new token is found."""
__author__ = 'Ka-Ping Yee <ping@lfw.org>'
__credits__ = \
@@ -111,7 +124,7 @@
except StopTokenizing:
pass
-# backwards compatible interface, probably not used
+# backwards compatible interface
def tokenize_loop(readline, tokeneater):
for token_info in generate_tokens(readline):
apply(tokeneater, token_info)