Initial commit

This commit is contained in:
Alex committed 2026-11-02 22:54:14 +08:00
commit 57fc3525eb
7311 files changed
+1291398

No files matched your search

@@ -0,0 +1,95 @@
import re
import string
###$ event <<expand-word>>
###$ win <Alt-slash>
###$ unix <Alt-slash>
class AutoExpand:
keydefs = {
"<<expand-word>>": ["<Alt-slash>"],
}
unix_keydefs = {
"<<expand-word>>": ["<Meta-slash>"],
}
menudefs = [
(
"edit",
[
("E_xpand word", "<<expand-word>>"),
],
),
]
wordchars = string.ascii_letters + string.digits + "_"
def __init__(self, editwin):
self.text = editwin.text
self.text.wordlist = None # XXX what is this?
self.state = None
def expand_word_event(self, event):
curinsert = self.text.index("insert")
curline = self.text.get("insert linestart", "insert lineend")
if not self.state:
words = self.getwords()
index = 0
else:
words, index, insert, line = self.state
if insert != curinsert or line != curline:
words = self.getwords()
index = 0
if not words:
self.text.bell()
return "break"
word = self.getprevword()
self.text.delete("insert - %d chars" % len(word), "insert")
newword = words[index]
index = (index + 1) % len(words)
if index == 0:
self.text.bell() # Warn we cycled around
self.text.insert("insert", newword)
curinsert = self.text.index("insert")
curline = self.text.get("insert linestart", "insert lineend")
self.state = words, index, curinsert, curline
return "break"
def getwords(self):
word = self.getprevword()
if not word:
return []
before = self.text.get("1.0", "insert wordstart")
wbefore = re.findall(r"\b" + word + r"\w+\b", before)
del before
after = self.text.get("insert wordend", "end")
wafter = re.findall(r"\b" + word + r"\w+\b", after)
del after
if not wbefore and not wafter:
return []
words = []
dict = {}
# search backwards through words before
wbefore.reverse()
for w in wbefore:
if dict.get(w):
continue
words.append(w)
dict[w] = w
# search onwards through words after
for w in wafter:
if dict.get(w):
continue
words.append(w)
dict[w] = w
words.append(word)
return words
def getprevword(self):
line = self.text.get("insert linestart", "insert")
i = len(line)
while i > 0 and line[i - 1] in self.wordchars:
i -= 1
return line[i:]
@@ -0,0 +1,536 @@
import tokenize
from pywin import default_scintilla_encoding
from . import PyParse
class AutoIndent:
menudefs = [
(
"edit",
[
None,
("_Indent region", "<<indent-region>>"),
("_Dedent region", "<<dedent-region>>"),
("Comment _out region", "<<comment-region>>"),
("U_ncomment region", "<<uncomment-region>>"),
("Tabify region", "<<tabify-region>>"),
("Untabify region", "<<untabify-region>>"),
("Toggle tabs", "<<toggle-tabs>>"),
("New indent width", "<<change-indentwidth>>"),
],
),
]
keydefs = {
"<<smart-backspace>>": ["<Key-BackSpace>"],
"<<newline-and-indent>>": ["<Key-Return>", "<KP_Enter>"],
"<<smart-indent>>": ["<Key-Tab>"],
}
windows_keydefs = {
"<<indent-region>>": ["<Control-bracketright>"],
"<<dedent-region>>": ["<Control-bracketleft>"],
"<<comment-region>>": ["<Alt-Key-3>"],
"<<uncomment-region>>": ["<Alt-Key-4>"],
"<<tabify-region>>": ["<Alt-Key-5>"],
"<<untabify-region>>": ["<Alt-Key-6>"],
"<<toggle-tabs>>": ["<Alt-Key-t>"],
"<<change-indentwidth>>": ["<Alt-Key-u>"],
}
unix_keydefs = {
"<<indent-region>>": [
"<Alt-bracketright>",
"<Meta-bracketright>",
"<Control-bracketright>",
],
"<<dedent-region>>": [
"<Alt-bracketleft>",
"<Meta-bracketleft>",
"<Control-bracketleft>",
],
"<<comment-region>>": ["<Alt-Key-3>", "<Meta-Key-3>"],
"<<uncomment-region>>": ["<Alt-Key-4>", "<Meta-Key-4>"],
"<<tabify-region>>": ["<Alt-Key-5>", "<Meta-Key-5>"],
"<<untabify-region>>": ["<Alt-Key-6>", "<Meta-Key-6>"],
"<<toggle-tabs>>": ["<Alt-Key-t>"],
"<<change-indentwidth>>": ["<Alt-Key-u>"],
}
# usetabs true -> literal tab characters are used by indent and
# dedent cmds, possibly mixed with spaces if
# indentwidth is not a multiple of tabwidth
# false -> tab characters are converted to spaces by indent
# and dedent cmds, and ditto TAB keystrokes
# indentwidth is the number of characters per logical indent level.
# tabwidth is the display width of a literal tab character.
# CAUTION: telling Tk to use anything other than its default
# tab setting causes it to use an entirely different tabbing algorithm,
# treating tab stops as fixed distances from the left margin.
# Nobody expects this, so for now tabwidth should never be changed.
usetabs = 1
indentwidth = 4
tabwidth = 8 # for IDLE use, must remain 8 until Tk is fixed
# If context_use_ps1 is true, parsing searches back for a ps1 line;
# else searches for a popular (if, def, ...) Python stmt.
context_use_ps1 = 0
# When searching backwards for a reliable place to begin parsing,
# first start num_context_lines[0] lines back, then
# num_context_lines[1] lines back if that didn't work, and so on.
# The last value should be huge (larger than the # of lines in a
# conceivable file).
# Making the initial values larger slows things down more often.
num_context_lines = 50, 500, 5000000
def __init__(self, editwin):
self.editwin = editwin
self.text = editwin.text
def config(self, **options):
for key, value in options.items():
if key == "usetabs":
self.usetabs = value
elif key == "indentwidth":
self.indentwidth = value
elif key == "tabwidth":
self.tabwidth = value
elif key == "context_use_ps1":
self.context_use_ps1 = value
else:
raise KeyError(f"bad option name: {key!r}")
# If ispythonsource and guess are true, guess a good value for
# indentwidth based on file content (if possible), and if
# indentwidth != tabwidth set usetabs false.
# In any case, adjust the Text widget's view of what a tab
# character means.
def set_indentation_params(self, ispythonsource, guess=1):
if guess and ispythonsource:
i = self.guess_indent()
if 2 <= i <= 8:
self.indentwidth = i
if self.indentwidth != self.tabwidth:
self.usetabs = 0
self.editwin.set_tabwidth(self.tabwidth)
def smart_backspace_event(self, event):
text = self.text
first, last = self.editwin.get_selection_indices()
if first and last:
text.delete(first, last)
text.mark_set("insert", first)
return "break"
# Delete whitespace left, until hitting a real char or closest
# preceding virtual tab stop.
chars = text.get("insert linestart", "insert")
if chars == "":
if text.compare("insert", ">", "1.0"):
# easy: delete preceding newline
text.delete("insert-1c")
else:
text.bell() # at start of buffer
return "break"
if chars[-1] not in " \t":
# easy: delete preceding real char
text.delete("insert-1c")
return "break"
# Ick. It may require *inserting* spaces if we back up over a
# tab character! This is written to be clear, not fast.
have = len(chars.expandtabs(self.tabwidth))
assert have > 0
want = int((have - 1) / self.indentwidth) * self.indentwidth
ncharsdeleted = 0
while 1:
chars = chars[:-1]
ncharsdeleted += 1
have = len(chars.expandtabs(self.tabwidth))
if have <= want or chars[-1] not in " \t":
break
text.undo_block_start()
text.delete("insert-%dc" % ncharsdeleted, "insert")
if have < want:
text.insert("insert", " " * (want - have))
text.undo_block_stop()
return "break"
def smart_indent_event(self, event):
# if intraline selection:
# delete it
# elif multiline selection:
# do indent-region & return
# indent one level
text = self.text
first, last = self.editwin.get_selection_indices()
text.undo_block_start()
try:
if first and last:
if index2line(first) != index2line(last):
return self.indent_region_event(event)
text.delete(first, last)
text.mark_set("insert", first)
prefix = text.get("insert linestart", "insert")
raw, effective = classifyws(prefix, self.tabwidth)
if raw == len(prefix):
# only whitespace to the left
self.reindent_to(effective + self.indentwidth)
else:
if self.usetabs:
pad = "\t"
else:
effective = len(prefix.expandtabs(self.tabwidth))
n = self.indentwidth
pad = " " * (n - effective % n)
text.insert("insert", pad)
text.see("insert")
return "break"
finally:
text.undo_block_stop()
def newline_and_indent_event(self, event):
text = self.text
first, last = self.editwin.get_selection_indices()
text.undo_block_start()
try:
if first and last:
text.delete(first, last)
text.mark_set("insert", first)
line = text.get("insert linestart", "insert")
i, n = 0, len(line)
while i < n and line[i] in " \t":
i += 1
if i == n:
# the cursor is in or at leading indentation; just inject
# an empty line at the start and strip space from current line
text.delete("insert - %d chars" % i, "insert")
text.insert("insert linestart", "\n")
return "break"
indent = line[:i]
# strip whitespace before insert point
i = 0
while line and line[-1] in " \t":
line = line[:-1]
i += 1
if i:
text.delete("insert - %d chars" % i, "insert")
# strip whitespace after insert point
while text.get("insert") in " \t":
text.delete("insert")
# start new line
text.insert("insert", "\n")
# adjust indentation for continuations and block
# open/close first need to find the last stmt
lno = index2line(text.index("insert"))
y = PyParse.Parser(self.indentwidth, self.tabwidth)
for context in self.num_context_lines:
startat = max(lno - context, 1)
startatindex = f"{startat!r}.0"
rawtext = text.get(startatindex, "insert")
y.set_str(rawtext)
bod = y.find_good_parse_start(
self.context_use_ps1, self._build_char_in_string_func(startatindex)
)
if bod is not None or startat == 1:
break
y.set_lo(bod or 0)
c = y.get_continuation_type()
if c != PyParse.C_NONE:
# The current stmt hasn't ended yet.
if c == PyParse.C_STRING:
# inside a string; just mimic the current indent
text.insert("insert", indent)
elif c == PyParse.C_BRACKET:
# line up with the first (if any) element of the
# last open bracket structure; else indent one
# level beyond the indent of the line with the
# last open bracket
self.reindent_to(y.compute_bracket_indent())
elif c == PyParse.C_BACKSLASH:
# if more than one line in this stmt already, just
# mimic the current indent; else if initial line
# has a start on an assignment stmt, indent to
# beyond leftmost =; else to beyond first chunk of
# non-whitespace on initial line
if y.get_num_lines_in_stmt() > 1:
text.insert("insert", indent)
else:
self.reindent_to(y.compute_backslash_indent())
else:
raise ValueError(f"bogus continuation type {c!r}")
return "break"
# This line starts a brand new stmt; indent relative to
# indentation of initial line of closest preceding
# interesting stmt.
indent = y.get_base_indent_string()
text.insert("insert", indent)
if y.is_block_opener():
self.smart_indent_event(event)
elif indent and y.is_block_closer():
self.smart_backspace_event(event)
return "break"
finally:
text.see("insert")
text.undo_block_stop()
auto_indent = newline_and_indent_event
# Our editwin provides a is_char_in_string function that works
# with a Tk text index, but PyParse only knows about offsets into
# a string. This builds a function for PyParse that accepts an
# offset.
def _build_char_in_string_func(self, startindex):
def inner(offset, _startindex=startindex, _icis=self.editwin.is_char_in_string):
return _icis(_startindex + "+%dc" % offset)
return inner
def indent_region_event(self, event):
head, tail, chars, lines = self.get_region()
for pos in range(len(lines)):
line = lines[pos]
if line:
raw, effective = classifyws(line, self.tabwidth)
effective += self.indentwidth
lines[pos] = self._make_blanks(effective) + line[raw:]
self.set_region(head, tail, chars, lines)
return "break"
def dedent_region_event(self, event):
head, tail, chars, lines = self.get_region()
for pos in range(len(lines)):
line = lines[pos]
if line:
raw, effective = classifyws(line, self.tabwidth)
effective = max(effective - self.indentwidth, 0)
lines[pos] = self._make_blanks(effective) + line[raw:]
self.set_region(head, tail, chars, lines)
return "break"
def comment_region_event(self, event):
head, tail, chars, lines = self.get_region()
for pos in range(len(lines) - 1):
line = lines[pos]
lines[pos] = "##" + line
self.set_region(head, tail, chars, lines)
def uncomment_region_event(self, event):
head, tail, chars, lines = self.get_region()
for pos in range(len(lines)):
line = lines[pos]
if not line:
continue
if line[:2] == "##":
line = line[2:]
elif line[:1] == "#":
line = line[1:]
lines[pos] = line
self.set_region(head, tail, chars, lines)
def tabify_region_event(self, event):
head, tail, chars, lines = self.get_region()
tabwidth = self._asktabwidth()
for pos in range(len(lines)):
line = lines[pos]
if line:
raw, effective = classifyws(line, tabwidth)
ntabs, nspaces = divmod(effective, tabwidth)
lines[pos] = "\t" * ntabs + " " * nspaces + line[raw:]
self.set_region(head, tail, chars, lines)
def untabify_region_event(self, event):
head, tail, chars, lines = self.get_region()
tabwidth = self._asktabwidth()
for pos in range(len(lines)):
lines[pos] = lines[pos].expandtabs(tabwidth)
self.set_region(head, tail, chars, lines)
def toggle_tabs_event(self, event):
if self.editwin.askyesno(
"Toggle tabs",
"Turn tabs " + ("on", "off")[self.usetabs] + "?",
parent=self.text,
):
self.usetabs = not self.usetabs
return "break"
# XXX this isn't bound to anything -- see class tabwidth comments
def change_tabwidth_event(self, event):
new = self._asktabwidth()
if new != self.tabwidth:
self.tabwidth = new
self.set_indentation_params(0, guess=0)
return "break"
def change_indentwidth_event(self, event):
new = self.editwin.askinteger(
"Indent width",
"New indent width (1-16)",
parent=self.text,
initialvalue=self.indentwidth,
minvalue=1,
maxvalue=16,
)
if new and new != self.indentwidth:
self.indentwidth = new
return "break"
def get_region(self):
text = self.text
first, last = self.editwin.get_selection_indices()
if first and last:
head = text.index(first + " linestart")
tail = text.index(last + "-1c lineend +1c")
else:
head = text.index("insert linestart")
tail = text.index("insert lineend +1c")
chars = text.get(head, tail)
lines = chars.split("\n")
return head, tail, chars, lines
def set_region(self, head, tail, chars, lines):
text = self.text
newchars = "\n".join(lines)
if newchars == chars:
text.bell()
return
text.tag_remove("sel", "1.0", "end")
text.mark_set("insert", head)
text.undo_block_start()
text.delete(head, tail)
text.insert(head, newchars)
text.undo_block_stop()
text.tag_add("sel", head, "insert")
# Make string that displays as n leading blanks.
def _make_blanks(self, n):
if self.usetabs:
ntabs, nspaces = divmod(n, self.tabwidth)
return "\t" * ntabs + " " * nspaces
else:
return " " * n
# Delete from beginning of line to insert point, then reinsert
# column logical (meaning use tabs if appropriate) spaces.
def reindent_to(self, column):
text = self.text
text.undo_block_start()
if text.compare("insert linestart", "!=", "insert"):
text.delete("insert linestart", "insert")
if column:
text.insert("insert", self._make_blanks(column))
text.undo_block_stop()
def _asktabwidth(self):
return (
self.editwin.askinteger(
"Tab width",
"Spaces per tab?",
parent=self.text,
initialvalue=self.tabwidth,
minvalue=1,
maxvalue=16,
)
or self.tabwidth
)
# Guess indentwidth from text content.
# Return guessed indentwidth. This should not be believed unless
# it's in a reasonable range (e.g., it will be 0 if no indented
# blocks are found).
def guess_indent(self):
opener, indented = IndentSearcher(self.text, self.tabwidth).run()
if opener and indented:
raw, indentsmall = classifyws(opener, self.tabwidth)
raw, indentlarge = classifyws(indented, self.tabwidth)
else:
indentsmall = indentlarge = 0
return indentlarge - indentsmall
# "line.col" -> line, as an int
def index2line(index):
return int(float(index))
# Look at the leading whitespace in s.
# Return pair (# of leading ws characters,
# effective # of leading blanks after expanding
# tabs to width tabwidth)
def classifyws(s, tabwidth):
raw = effective = 0
for ch in s:
if ch == " ":
raw += 1
effective += 1
elif ch == "\t":
raw += 1
effective = (effective // tabwidth + 1) * tabwidth
else:
break
return raw, effective
class IndentSearcher:
# .run() chews over the Text widget, looking for a block opener
# and the stmt following it. Returns a pair,
# (line containing block opener, line containing stmt)
# Either or both may be None.
def __init__(self, text, tabwidth):
self.text = text
self.tabwidth = tabwidth
self.i = self.finished = 0
self.blkopenline = self.indentedline = None
def readline(self):
if self.finished:
val = ""
else:
i = self.i = self.i + 1
mark = f"{i!r}.0"
if self.text.compare(mark, ">=", "end"):
val = ""
else:
val = self.text.get(mark, mark + " lineend+1c")
# hrm - not sure this is correct - the source code may have
# an encoding declared, but the data will *always* be in
# default_scintilla_encoding - so if anyone looks at the encoding decl
# in the source they will be wrong. I think. Maybe. Or something...
return val.encode(default_scintilla_encoding)
def run(self):
OPENERS = ("class", "def", "for", "if", "try", "while")
INDENT = tokenize.INDENT
NAME = tokenize.NAME
save_tabsize = tokenize.tabsize
tokenize.tabsize = self.tabwidth
try:
try:
for typ, token, start, end, line in tokenize.tokenize(self.readline):
if typ == NAME and token in OPENERS:
self.blkopenline = line
elif typ == INDENT and self.blkopenline:
self.indentedline = line
break
except (tokenize.TokenError, IndentationError):
# since we cut off the tokenizer early, we can trigger
# spurious errors
pass
finally:
tokenize.tabsize = save_tabsize
return self.blkopenline, self.indentedline
@@ -0,0 +1,214 @@
# CallTips.py - An IDLE extension that provides "Call Tips" - ie, a floating window that
# displays parameter information as you open parens.
import inspect
import string
import sys
import traceback
class CallTips:
menudefs = []
keydefs = {
"<<paren-open>>": ["<Key-parenleft>"],
"<<paren-close>>": ["<Key-parenright>"],
"<<check-calltip-cancel>>": ["<KeyRelease>"],
"<<calltip-cancel>>": ["<ButtonPress>", "<Key-Escape>"],
}
windows_keydefs = {}
unix_keydefs = {}
def __init__(self, editwin):
self.editwin = editwin
self.text = editwin.text
self.calltip = None
if hasattr(self.text, "make_calltip_window"):
self._make_calltip_window = self.text.make_calltip_window
else:
self._make_calltip_window = self._make_tk_calltip_window
def close(self):
self._make_calltip_window = None
# Makes a Tk based calltip window. Used by IDLE, but not Pythonwin.
# See __init__ above for how this is used.
def _make_tk_calltip_window(self):
import CallTipWindow
return CallTipWindow.CallTip(self.text)
def _remove_calltip_window(self):
if self.calltip:
self.calltip.hidetip()
self.calltip = None
def paren_open_event(self, event):
self._remove_calltip_window()
arg_text = get_arg_text(self.get_object_at_cursor())
if arg_text:
self.calltip_start = self.text.index("insert")
self.calltip = self._make_calltip_window()
self.calltip.showtip(arg_text)
return "" # so the event is handled normally.
def paren_close_event(self, event):
# Now just hides, but later we should check if other
# paren'd expressions remain open.
self._remove_calltip_window()
return "" # so the event is handled normally.
def check_calltip_cancel_event(self, event):
if self.calltip:
# If we have moved before the start of the calltip,
# or off the calltip line, then cancel the tip.
# (Later need to be smarter about multi-line, etc)
if self.text.compare(
"insert", "<=", self.calltip_start
) or self.text.compare("insert", ">", self.calltip_start + " lineend"):
self._remove_calltip_window()
return "" # so the event is handled normally.
def calltip_cancel_event(self, event):
self._remove_calltip_window()
return "" # so the event is handled normally.
def get_object_at_cursor(
self,
wordchars="._"
+ string.ascii_uppercase
+ string.ascii_lowercase
+ string.digits,
):
# XXX - This needs to be moved to a better place
# so the "." attribute lookup code can also use it.
text = self.text
chars = text.get("insert linestart", "insert")
i = len(chars)
while i and chars[i - 1] in wordchars:
i -= 1
word = chars[i:]
if word:
# How is this for a hack!
import __main__
try:
return eval(word, sys.modules | __main__.__dict__)
except:
pass
return None # Can't find an object.
def _find_constructor(class_ob):
# Given a class object, return a function object used for the
# constructor (ie, __init__() ) or None if we can't find one.
try:
return class_ob.__init__
except AttributeError:
for base in class_ob.__bases__:
rc = _find_constructor(base)
if rc is not None:
return rc
return None
def get_arg_text(ob):
# Get a string describing the arguments for the given object.
argText = ""
if ob is not None:
if inspect.isclass(ob):
# Look for the highest __init__ in the class chain.
fob = _find_constructor(ob)
if fob is None:
fob = lambda: None
else:
fob = ob
if inspect.isfunction(fob) or inspect.ismethod(fob):
try:
argText = str(inspect.signature(fob))
except:
print("Failed to format the args")
traceback.print_exc()
# See if we can use the docstring
if hasattr(ob, "__doc__"):
doc = ob.__doc__
try:
doc = doc.strip()
pos = doc.find("\n")
except AttributeError:
## New style classes may have __doc__ slot without actually
## having a string assigned to it
pass
else:
if pos < 0 or pos > 70:
pos = 70
if argText:
argText += "\n"
argText += doc[:pos]
return argText
#################################################
#
# Test code
#
if __name__ == "__main__":
def t1():
"()"
def t2(a, b=None):
"(a, b=None)"
def t3(a, *args):
"(a, *args)"
def t4(*args):
"(*args)"
def t5(a, *args):
"(a, *args)"
def t6(a, b=None, *args, **kw):
"(a, b=None, *args, **kw)"
class TC:
"(self, a=None, *b)"
def __init__(self, a=None, *b):
"(self, a=None, *b)"
def t1(self):
"(self)"
def t2(self, a, b=None):
"(self, a, b=None)"
def t3(self, a, *args):
"(self, a, *args)"
def t4(self, *args):
"(self, *args)"
def t5(self, a, *args):
"(self, a, *args)"
def t6(self, a, b=None, *args, **kw):
"(self, a, b=None, *args, **kw)"
def test(tests):
failed = []
for t in tests:
expected = t.__doc__ + "\n" + t.__doc__
if get_arg_text(t) != expected:
failed.append(t)
print(f"{t} - expected {expected!r}, but got {get_arg_text(t)!r}")
print("%d of %d tests failed" % (len(failed), len(tests)))
tc = TC()
tests = t1, t2, t3, t4, t5, t6, TC, tc.t1, tc.t2, tc.t3, tc.t4, tc.t5, tc.t6
test(tests)
@@ -0,0 +1,166 @@
# Extension to format a paragraph
# Does basic, standard text formatting, and also understands Python
# comment blocks. Thus, for editing Python source code, this
# extension is really only suitable for reformatting these comment
# blocks or triple-quoted strings.
# Known problems with comment reformatting:
# * If there is a selection marked, and the first line of the
# selection is not complete, the block will probably not be detected
# as comments, and will have the normal "text formatting" rules
# applied.
# * If a comment block has leading whitespace that mixes tabs and
# spaces, they will not be considered part of the same block.
# * Fancy comments, like this bulleted list, aren't handled :-)
import re
class FormatParagraph:
menudefs = [
(
"edit",
[
("Format Paragraph", "<<format-paragraph>>"),
],
)
]
keydefs = {
"<<format-paragraph>>": ["<Alt-q>"],
}
unix_keydefs = {
"<<format-paragraph>>": ["<Meta-q>"],
}
def __init__(self, editwin):
self.editwin = editwin
def close(self):
self.editwin = None
def format_paragraph_event(self, event):
text = self.editwin.text
first, last = self.editwin.get_selection_indices()
if first and last:
data = text.get(first, last)
comment_header = ""
else:
first, last, comment_header, data = find_paragraph(
text, text.index("insert")
)
if comment_header:
# Reformat the comment lines - convert to text sans header.
lines = data.split("\n")
lines = map(lambda st, l=len(comment_header): st[l:], lines)
data = "\n".join(lines)
# Reformat to 70 chars or a 20 char width, whichever is greater.
format_width = max(70 - len(comment_header), 20)
newdata = reformat_paragraph(data, format_width)
# re-split and re-insert the comment header.
newdata = newdata.split("\n")
# If the block ends in a \n, we don't want the comment
# prefix inserted after it. (I'm not sure it makes sense to
# reformat a comment block that isn't made of complete
# lines, but whatever!) Can't think of a clean soltution,
# so we hack away
block_suffix = ""
if not newdata[-1]:
block_suffix = "\n"
newdata = newdata[:-1]
builder = lambda item, prefix=comment_header: prefix + item
newdata = "\n".join([builder(d) for d in newdata]) + block_suffix
else:
# Just a normal text format
newdata = reformat_paragraph(data)
text.tag_remove("sel", "1.0", "end")
if newdata != data:
text.mark_set("insert", first)
text.undo_block_start()
text.delete(first, last)
text.insert(first, newdata)
text.undo_block_stop()
else:
text.mark_set("insert", last)
text.see("insert")
def find_paragraph(text, mark):
lineno, col = list(map(int, mark.split(".")))
line = text.get("%d.0" % lineno, "%d.0 lineend" % lineno)
while text.compare("%d.0" % lineno, "<", "end") and is_all_white(line):
lineno += 1
line = text.get("%d.0" % lineno, "%d.0 lineend" % lineno)
first_lineno = lineno
comment_header = get_comment_header(line)
comment_header_len = len(comment_header)
while get_comment_header(line) == comment_header and not is_all_white(
line[comment_header_len:]
):
lineno += 1
line = text.get("%d.0" % lineno, "%d.0 lineend" % lineno)
last = "%d.0" % lineno
# Search back to beginning of paragraph
lineno = first_lineno - 1
line = text.get("%d.0" % lineno, "%d.0 lineend" % lineno)
while (
lineno > 0
and get_comment_header(line) == comment_header
and not is_all_white(line[comment_header_len:])
):
lineno -= 1
line = text.get("%d.0" % lineno, "%d.0 lineend" % lineno)
first = "%d.0" % (lineno + 1)
return first, last, comment_header, text.get(first, last)
def reformat_paragraph(data, limit=70):
lines = data.split("\n")
i = 0
n = len(lines)
while i < n and is_all_white(lines[i]):
i += 1
if i >= n:
return data
indent1 = get_indent(lines[i])
if i + 1 < n and not is_all_white(lines[i + 1]):
indent2 = get_indent(lines[i + 1])
else:
indent2 = indent1
new = lines[:i]
partial = indent1
while i < n and not is_all_white(lines[i]):
# XXX Should take double space after period (etc.) into account
words = re.split(r"(\s+)", lines[i])
for j in range(0, len(words), 2):
word = words[j]
if not word:
continue # Can happen when line ends in whitespace
if len((partial + word).expandtabs()) > limit and partial != indent1:
new.append(partial.rstrip())
partial = indent2
partial += word + " "
if j + 1 < len(words) and words[j + 1] != " ":
partial += " "
i += 1
new.append(partial.rstrip())
# XXX Should reformat remaining paragraphs as well
new.extend(lines[i:])
return "\n".join(new)
def is_all_white(line):
return re.match(r"^\s*$", line) is not None
def get_indent(line):
return re.match(r"^(\s*)", line).group()
def get_comment_header(line):
m = re.match(r"^(\s*#*)", line)
if m is None:
return ""
return m.group(1)
@@ -0,0 +1,87 @@
class History:
def __init__(self, text, output_sep="\n"):
self.text = text
self.history = []
self.history_prefix = None
self.history_pointer = None
self.output_sep = output_sep
text.bind("<<history-previous>>", self.history_prev)
text.bind("<<history-next>>", self.history_next)
def history_next(self, event):
self.history_do(0)
return "break"
def history_prev(self, event):
self.history_do(1)
return "break"
def _get_source(self, start, end):
# Get source code from start index to end index. Lines in the
# text control may be separated by sys.ps2 .
lines = self.text.get(start, end).split(self.output_sep)
return "\n".join(lines)
def _put_source(self, where, source):
output = self.output_sep.join(source.split("\n"))
self.text.insert(where, output)
def history_do(self, reverse):
nhist = len(self.history)
pointer = self.history_pointer
prefix = self.history_prefix
if pointer is not None and prefix is not None:
if (
self.text.compare("insert", "!=", "end-1c")
or self._get_source("iomark", "end-1c") != self.history[pointer]
):
pointer = prefix = None
if pointer is None or prefix is None:
prefix = self._get_source("iomark", "end-1c")
if reverse:
pointer = nhist
else:
pointer = -1
nprefix = len(prefix)
while 1:
if reverse:
pointer -= 1
else:
pointer += 1
if pointer < 0 or pointer >= nhist:
self.text.bell()
if self._get_source("iomark", "end-1c") != prefix:
self.text.delete("iomark", "end-1c")
self._put_source("iomark", prefix)
pointer = prefix = None
break
item = self.history[pointer]
if item[:nprefix] == prefix and len(item) > nprefix:
self.text.delete("iomark", "end-1c")
self._put_source("iomark", item)
break
self.text.mark_set("insert", "end-1c")
self.text.see("insert")
self.text.tag_remove("sel", "1.0", "end")
self.history_pointer = pointer
self.history_prefix = prefix
def history_store(self, source):
source = source.strip()
if len(source) > 2:
# avoid duplicates
try:
self.history.remove(source)
except ValueError:
pass
self.history.append(source)
self.history_pointer = None
self.history_prefix = None
def recall(self, s):
s = s.strip()
self.text.tag_remove("sel", "1.0", "end")
self.text.delete("iomark", "end-1c")
self.text.mark_set("insert", "end-1c")
self.text.insert("insert", s)
self.text.see("insert")
@@ -0,0 +1,246 @@
A. HISTORY OF THE SOFTWARE
==========================
Python was created in the early 1990s by Guido van Rossum at Stichting
Mathematisch Centrum (CWI, see http://www.cwi.nl) in the Netherlands
as a successor of a language called ABC. Guido remains Python's
principal author, although it includes many contributions from others.
In 1995, Guido continued his work on Python at the Corporation for
National Research Initiatives (CNRI, see http://www.cnri.reston.va.us)
in Reston, Virginia where he released several versions of the
software.
In May 2000, Guido and the Python core development team moved to
BeOpen.com to form the BeOpen PythonLabs team. In October of the same
year, the PythonLabs team moved to Digital Creations (see
http://www.digicool.com). In 2001, the Python Software Foundation
(PSF, see http://www.python.org/psf/) was formed, a non-profit
organization created specifically to own Python-related Intellectual
Property. Digital Creations is a sponsoring member of the PSF.
All Python releases are Open Source (see http://www.opensource.org for
the Open Source Definition). Historically, most, but not all, Python
releases have also been GPL-compatible; the table below summarizes
the various releases.
Release Derived Year Owner GPL-
from compatible? (1)
0.9.0 thru 1.2 1991-1995 CWI yes
1.3 thru 1.5.2 1.2 1995-1999 CNRI yes
1.6 1.5.2 2000 CNRI no
2.0 1.6 2000 BeOpen.com no
1.6.1 1.6 2001 CNRI no
2.1 2.0+1.6.1 2001 PSF no
2.0.1 2.0+1.6.1 2001 PSF yes
2.1.1 2.1+2.0.1 2001 PSF yes
2.2 2.1.1 2001 PSF yes
Footnotes:
(1) GPL-compatible doesn't mean that we're distributing Python under
the GPL. All Python licenses, unlike the GPL, let you distribute
a modified version without making your changes open source. The
GPL-compatible licenses make it possible to combine Python with
other software that is released under the GPL; the others don't.
Thanks to the many outside volunteers who have worked under Guido's
direction to make these releases possible.
B. TERMS AND CONDITIONS FOR ACCESSING OR OTHERWISE USING PYTHON
===============================================================
PSF LICENSE AGREEMENT FOR PYTHON 2.2
------------------------------------
1. This LICENSE AGREEMENT is between the Python Software Foundation
("PSF"), and the Individual or Organization ("Licensee") accessing and
otherwise using Python 2.2 software in source or binary form and its
associated documentation.
2. Subject to the terms and conditions of this License Agreement, PSF
hereby grants Licensee a nonexclusive, royalty-free, world-wide
license to reproduce, analyze, test, perform and/or display publicly,
prepare derivative works, distribute, and otherwise use Python 2.2
alone or in any derivative version, provided, however, that PSF's
License Agreement and PSF's notice of copyright, i.e., "Copyright (c)
2001 Python Software Foundation; All Rights Reserved" are retained in
Python 2.2 alone or in any derivative version prepared by Licensee.
3. In the event Licensee prepares a derivative work that is based on
or incorporates Python 2.2 or any part thereof, and wants to make
the derivative work available to others as provided herein, then
Licensee hereby agrees to include in any such work a brief summary of
the changes made to Python 2.2.
4. PSF is making Python 2.2 available to Licensee on an "AS IS"
basis. PSF MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, PSF MAKES NO AND
DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS
FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON 2.2 WILL NOT
INFRINGE ANY THIRD PARTY RIGHTS.
5. PSF SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON
2.2 FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS AS
A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON 2.2,
OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF.
6. This License Agreement will automatically terminate upon a material
breach of its terms and conditions.
7. Nothing in this License Agreement shall be deemed to create any
relationship of agency, partnership, or joint venture between PSF and
Licensee. This License Agreement does not grant permission to use PSF
trademarks or trade name in a trademark sense to endorse or promote
products or services of Licensee, or any third party.
8. By copying, installing or otherwise using Python 2.2, Licensee
agrees to be bound by the terms and conditions of this License
Agreement.
BEOPEN.COM LICENSE AGREEMENT FOR PYTHON 2.0
-------------------------------------------
BEOPEN PYTHON OPEN SOURCE LICENSE AGREEMENT VERSION 1
1. This LICENSE AGREEMENT is between BeOpen.com ("BeOpen"), having an
office at 160 Saratoga Avenue, Santa Clara, CA 95051, and the
Individual or Organization ("Licensee") accessing and otherwise using
this software in source or binary form and its associated
documentation ("the Software").
2. Subject to the terms and conditions of this BeOpen Python License
Agreement, BeOpen hereby grants Licensee a non-exclusive,
royalty-free, world-wide license to reproduce, analyze, test, perform
and/or display publicly, prepare derivative works, distribute, and
otherwise use the Software alone or in any derivative version,
provided, however, that the BeOpen Python License is retained in the
Software, alone or in any derivative version prepared by Licensee.
3. BeOpen is making the Software available to Licensee on an "AS IS"
basis. BEOPEN MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, BEOPEN MAKES NO AND
DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS
FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF THE SOFTWARE WILL NOT
INFRINGE ANY THIRD PARTY RIGHTS.
4. BEOPEN SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF THE
SOFTWARE FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS
AS A RESULT OF USING, MODIFYING OR DISTRIBUTING THE SOFTWARE, OR ANY
DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF.
5. This License Agreement will automatically terminate upon a material
breach of its terms and conditions.
6. This License Agreement shall be governed by and interpreted in all
respects by the law of the State of California, excluding conflict of
law provisions. Nothing in this License Agreement shall be deemed to
create any relationship of agency, partnership, or joint venture
between BeOpen and Licensee. This License Agreement does not grant
permission to use BeOpen trademarks or trade names in a trademark
sense to endorse or promote products or services of Licensee, or any
third party. As an exception, the "BeOpen Python" logos available at
http://www.pythonlabs.com/logos.html may be used according to the
permissions granted on that web page.
7. By copying, installing or otherwise using the software, Licensee
agrees to be bound by the terms and conditions of this License
Agreement.
CNRI LICENSE AGREEMENT FOR PYTHON 1.6.1
---------------------------------------
1. This LICENSE AGREEMENT is between the Corporation for National
Research Initiatives, having an office at 1895 Preston White Drive,
Reston, VA 20191 ("CNRI"), and the Individual or Organization
("Licensee") accessing and otherwise using Python 1.6.1 software in
source or binary form and its associated documentation.
2. Subject to the terms and conditions of this License Agreement, CNRI
hereby grants Licensee a nonexclusive, royalty-free, world-wide
license to reproduce, analyze, test, perform and/or display publicly,
prepare derivative works, distribute, and otherwise use Python 1.6.1
alone or in any derivative version, provided, however, that CNRI's
License Agreement and CNRI's notice of copyright, i.e., "Copyright (c)
1995-2001 Corporation for National Research Initiatives; All Rights
Reserved" are retained in Python 1.6.1 alone or in any derivative
version prepared by Licensee. Alternately, in lieu of CNRI's License
Agreement, Licensee may substitute the following text (omitting the
quotes): "Python 1.6.1 is made available subject to the terms and
conditions in CNRI's License Agreement. This Agreement together with
Python 1.6.1 may be located on the Internet using the following
unique, persistent identifier (known as a handle): 1895.22/1013. This
Agreement may also be obtained from a proxy server on the Internet
using the following URL: http://hdl.handle.net/1895.22/1013".
3. In the event Licensee prepares a derivative work that is based on
or incorporates Python 1.6.1 or any part thereof, and wants to make
the derivative work available to others as provided herein, then
Licensee hereby agrees to include in any such work a brief summary of
the changes made to Python 1.6.1.
4. CNRI is making Python 1.6.1 available to Licensee on an "AS IS"
basis. CNRI MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, CNRI MAKES NO AND
DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS
FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON 1.6.1 WILL NOT
INFRINGE ANY THIRD PARTY RIGHTS.
5. CNRI SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON
1.6.1 FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR LOSS AS
A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON 1.6.1,
OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF THE POSSIBILITY THEREOF.
6. This License Agreement will automatically terminate upon a material
breach of its terms and conditions.
7. This License Agreement shall be governed by the federal
intellectual property law of the United States, including without
limitation the federal copyright law, and, to the extent such
U.S. federal law does not apply, by the law of the Commonwealth of
Virginia, excluding Virginia's conflict of law provisions.
Notwithstanding the foregoing, with regard to derivative works based
on Python 1.6.1 that incorporate non-separable material that was
previously distributed under the GNU General Public License (GPL), the
law of the Commonwealth of Virginia shall govern this License
Agreement only as to issues arising under or with respect to
Paragraphs 4, 5, and 7 of this License Agreement. Nothing in this
License Agreement shall be deemed to create any relationship of
agency, partnership, or joint venture between CNRI and Licensee. This
License Agreement does not grant permission to use CNRI trademarks or
trade name in a trademark sense to endorse or promote products or
services of Licensee, or any third party.
8. By clicking on the "ACCEPT" button where indicated, or by copying,
installing or otherwise using Python 1.6.1, Licensee agrees to be
bound by the terms and conditions of this License Agreement.
ACCEPT
CWI LICENSE AGREEMENT FOR PYTHON 0.9.0 THROUGH 1.2
--------------------------------------------------
Copyright (c) 1991 - 1995, Stichting Mathematisch Centrum Amsterdam,
The Netherlands. All rights reserved.
Permission to use, copy, modify, and distribute this software and its
documentation for any purpose and without fee is hereby granted,
provided that the above copyright notice appear in all copies and that
both that copyright notice and this permission notice appear in
supporting documentation, and that the name of Stichting Mathematisch
Centrum or CWI not be used in advertising or publicity pertaining to
distribution of the software without specific, written prior
permission.
STICHTING MATHEMATISCH CENTRUM DISCLAIMS ALL WARRANTIES WITH REGARD TO
THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
FITNESS, IN NO EVENT SHALL STICHTING MATHEMATISCH CENTRUM BE LIABLE
FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
@@ -0,0 +1,585 @@
import re
import sys
# Reason last stmt is continued (or C_NONE if it's not).
C_NONE, C_BACKSLASH, C_STRING, C_BRACKET = list(range(4))
if 0: # for throwaway debugging output
def dump(*stuff):
sys.__stdout__.write(" ".join(map(str, stuff)) + "\n")
# Find what looks like the start of a popular stmt.
_synchre = re.compile(
r"""
^
[ \t]*
(?: if
| for
| while
| else
| def
| return
| assert
| break
| class
| continue
| elif
| try
| except
| raise
| import
)
\b
""",
re.VERBOSE | re.MULTILINE,
).search
# Match blank line or non-indenting comment line.
_junkre = re.compile(
r"""
[ \t]*
(?: \# \S .* )?
\n
""",
re.VERBOSE,
).match
# Match any flavor of string; the terminating quote is optional
# so that we're robust in the face of incomplete program text.
_match_stringre = re.compile(
r"""
\""" [^"\\]* (?:
(?: \\. | "(?!"") )
[^"\\]*
)*
(?: \""" )?
| " [^"\\\n]* (?: \\. [^"\\\n]* )* "?
| ''' [^'\\]* (?:
(?: \\. | '(?!'') )
[^'\\]*
)*
(?: ''' )?
| ' [^'\\\n]* (?: \\. [^'\\\n]* )* '?
""",
re.VERBOSE | re.DOTALL,
).match
# Match a line that starts with something interesting;
# used to find the first item of a bracket structure.
_itemre = re.compile(
r"""
[ \t]*
[^\s#\\] # if we match, m.end()-1 is the interesting char
""",
re.VERBOSE,
).match
# Match start of stmts that should be followed by a dedent.
_closere = re.compile(
r"""
\s*
(?: return
| break
| continue
| raise
| pass
)
\b
""",
re.VERBOSE,
).match
# Chew up non-special chars as quickly as possible. If match is
# successful, m.end() less 1 is the index of the last boring char
# matched. If match is unsuccessful, the string starts with an
# interesting char.
_chew_ordinaryre = re.compile(
r"""
[^[\](){}#'"\\]+
""",
re.VERBOSE,
).match
# Build translation table to map uninteresting chars to "x", open
# brackets to "(", and close brackets to ")".
_tran = ["x"] * 256
for ch in "({[":
_tran[ord(ch)] = "("
for ch in ")}]":
_tran[ord(ch)] = ")"
for ch in "\"'\\\n#":
_tran[ord(ch)] = ch
del ch
class Parser:
def __init__(self, indentwidth, tabwidth):
self.indentwidth = indentwidth
self.tabwidth = tabwidth
def set_str(self, str):
assert len(str) == 0 or str[-1] == "\n", f"Oops - have str {str!r}"
self.str = str
self.study_level = 0
# Return index of a good place to begin parsing, as close to the
# end of the string as possible. This will be the start of some
# popular stmt like "if" or "def". Return None if none found:
# the caller should pass more prior context then, if possible, or
# if not (the entire program text up until the point of interest
# has already been tried) pass 0 to set_lo.
#
# This will be reliable iff given a reliable is_char_in_string
# function, meaning that when it says "no", it's absolutely
# guaranteed that the char is not in a string.
#
# Ack, hack: in the shell window this kills us, because there's
# no way to tell the differences between output, >>> etc and
# user input. Indeed, IDLE's first output line makes the rest
# look like it's in an unclosed paren!:
# Python X.X.X (#0, Apr 13 1999, ...
def find_good_parse_start(self, use_ps1, is_char_in_string=None):
str, pos = self.str, None
if use_ps1:
# shell window
ps1 = "\n" + sys.ps1
i = str.rfind(ps1)
if i >= 0:
pos = i + len(ps1)
# make it look like there's a newline instead
# of ps1 at the start -- hacking here once avoids
# repeated hackery later
self.str = str[: pos - 1] + "\n" + str[pos:]
return pos
# File window -- real work.
if not is_char_in_string:
# no clue -- make the caller pass everything
return None
# Peek back from the end for a good place to start,
# but don't try too often; pos will be left None, or
# bumped to a legitimate synch point.
limit = len(str)
for tries in range(5):
i = str.rfind(":\n", 0, limit)
if i < 0:
break
i = str.rfind("\n", 0, i) + 1 # start of colon line
m = _synchre(str, i, limit)
if m and not is_char_in_string(m.start()):
pos = m.start()
break
limit = i
if pos is None:
# Nothing looks like a block-opener, or stuff does
# but is_char_in_string keeps returning true; most likely
# we're in or near a giant string, the colorizer hasn't
# caught up enough to be helpful, or there simply *aren't*
# any interesting stmts. In any of these cases we're
# going to have to parse the whole thing to be sure, so
# give it one last try from the start, but stop wasting
# time here regardless of the outcome.
m = _synchre(str)
if m and not is_char_in_string(m.start()):
pos = m.start()
return pos
# Peeking back worked; look forward until _synchre no longer
# matches.
i = pos + 1
while 1:
m = _synchre(str, i)
if m:
s, i = m.span()
if not is_char_in_string(s):
pos = s
else:
break
return pos
# Throw away the start of the string. Intended to be called with
# find_good_parse_start's result.
def set_lo(self, lo):
assert lo == 0 or self.str[lo - 1] == "\n"
if lo > 0:
self.str = self.str[lo:]
# As quickly as humanly possible <wink>, find the line numbers (0-
# based) of the non-continuation lines.
# Creates self.{goodlines, continuation}.
def _study1(self):
if self.study_level >= 1:
return
self.study_level = 1
# Map all uninteresting characters to "x", all open brackets
# to "(", all close brackets to ")", then collapse runs of
# uninteresting characters. This can cut the number of chars
# by a factor of 10-40, and so greatly speed the following loop.
str = self.str
str = str.translate(_tran)
str = str.replace("xxxxxxxx", "x")
str = str.replace("xxxx", "x")
str = str.replace("xx", "x")
str = str.replace("xx", "x")
str = str.replace("\nx", "\n")
# note that replacing x\n with \n would be incorrect, because
# x may be preceded by a backslash
# March over the squashed version of the program, accumulating
# the line numbers of non-continued stmts, and determining
# whether & why the last stmt is a continuation.
continuation = C_NONE
level = lno = 0 # level is nesting level; lno is line number
self.goodlines = goodlines = [0]
push_good = goodlines.append
i, n = 0, len(str)
while i < n:
ch = str[i]
i += 1
# cases are checked in decreasing order of frequency
if ch == "x":
continue
if ch == "\n":
lno += 1
if level == 0:
push_good(lno)
# else we're in an unclosed bracket structure
continue
if ch == "(":
level += 1
continue
if ch == ")":
if level:
level -= 1
# else the program is invalid, but we can't complain
continue
if ch == '"' or ch == "'":
# consume the string
quote = ch
if str[i - 1 : i + 2] == quote * 3:
quote *= 3
w = len(quote) - 1
i += w
while i < n:
ch = str[i]
i += 1
if ch == "x":
continue
if str[i - 1 : i + w] == quote:
i += w
break
if ch == "\n":
lno += 1
if w == 0:
# unterminated single-quoted string
if level == 0:
push_good(lno)
break
continue
if ch == "\\":
assert i < n
if str[i] == "\n":
lno += 1
i += 1
continue
# else comment char or paren inside string
else:
# didn't break out of the loop, so we're still
# inside a string
continuation = C_STRING
continue # with outer loop
if ch == "#":
# consume the comment
i = str.find("\n", i)
assert i >= 0
continue
assert ch == "\\"
assert i < n
if str[i] == "\n":
lno += 1
if i + 1 == n:
continuation = C_BACKSLASH
i += 1
# The last stmt may be continued for all 3 reasons.
# String continuation takes precedence over bracket
# continuation, which beats backslash continuation.
if continuation != C_STRING and level > 0:
continuation = C_BRACKET
self.continuation = continuation
# Push the final line number as a sentinel value, regardless of
# whether it's continued.
assert (continuation == C_NONE) == (goodlines[-1] == lno)
if goodlines[-1] != lno:
push_good(lno)
def get_continuation_type(self):
self._study1()
return self.continuation
# study1 was sufficient to determine the continuation status,
# but doing more requires looking at every character. study2
# does this for the last interesting statement in the block.
# Creates:
# self.stmt_start, stmt_end
# slice indices of last interesting stmt
# self.lastch
# last non-whitespace character before optional trailing
# comment
# self.lastopenbracketpos
# if continuation is C_BRACKET, index of last open bracket
def _study2(self):
if self.study_level >= 2:
return
self._study1()
self.study_level = 2
# Set p and q to slice indices of last interesting stmt.
str, goodlines = self.str, self.goodlines
i = len(goodlines) - 1
p = len(str) # index of newest line
while i:
assert p
# p is the index of the stmt at line number goodlines[i].
# Move p back to the stmt at line number goodlines[i-1].
q = p
for nothing in range(goodlines[i - 1], goodlines[i]):
# tricky: sets p to 0 if no preceding newline
p = str.rfind("\n", 0, p - 1) + 1
# The stmt str[p:q] isn't a continuation, but may be blank
# or a non-indenting comment line.
if _junkre(str, p):
i -= 1
else:
break
if i == 0:
# nothing but junk!
assert p == 0
q = p
self.stmt_start, self.stmt_end = p, q
# Analyze this stmt, to find the last open bracket (if any)
# and last interesting character (if any).
lastch = ""
stack = [] # stack of open bracket indices
push_stack = stack.append
while p < q:
# suck up all except ()[]{}'"#\\
m = _chew_ordinaryre(str, p, q)
if m:
# we skipped at least one boring char
newp = m.end()
# back up over totally boring whitespace
i = newp - 1 # index of last boring char
while i >= p and str[i] in " \t\n":
i -= 1
if i >= p:
lastch = str[i]
p = newp
if p >= q:
break
ch = str[p]
if ch in "([{":
push_stack(p)
lastch = ch
p += 1
continue
if ch in ")]}":
if stack:
del stack[-1]
lastch = ch
p += 1
continue
if ch == '"' or ch == "'":
# consume string
# Note that study1 did this with a Python loop, but
# we use a regexp here; the reason is speed in both
# cases; the string may be huge, but study1 pre-squashed
# strings to a couple of characters per line. study1
# also needed to keep track of newlines, and we don't
# have to.
lastch = ch
p = _match_stringre(str, p, q).end()
continue
if ch == "#":
# consume comment and trailing newline
p = str.find("\n", p, q) + 1
assert p > 0
continue
assert ch == "\\"
p += 1 # beyond backslash
assert p < q
if str[p] != "\n":
# the program is invalid, but can't complain
lastch = ch + str[p]
p += 1 # beyond escaped char
# end while p < q:
self.lastch = lastch
if stack:
self.lastopenbracketpos = stack[-1]
# Assuming continuation is C_BRACKET, return the number
# of spaces the next line should be indented.
def compute_bracket_indent(self):
self._study2()
assert self.continuation == C_BRACKET
j = self.lastopenbracketpos
str = self.str
n = len(str)
origi = i = str.rfind("\n", 0, j) + 1
j += 1 # one beyond open bracket
# find first list item; set i to start of its line
while j < n:
m = _itemre(str, j)
if m:
j = m.end() - 1 # index of first interesting char
extra = 0
break
else:
# this line is junk; advance to next line
i = j = str.find("\n", j) + 1
else:
# nothing interesting follows the bracket;
# reproduce the bracket line's indentation + a level
j = i = origi
while str[j] in " \t":
j += 1
extra = self.indentwidth
return len(str[i:j].expandtabs(self.tabwidth)) + extra
# Return number of physical lines in last stmt (whether or not
# it's an interesting stmt! this is intended to be called when
# continuation is C_BACKSLASH).
def get_num_lines_in_stmt(self):
self._study1()
goodlines = self.goodlines
return goodlines[-1] - goodlines[-2]
# Assuming continuation is C_BACKSLASH, return the number of spaces
# the next line should be indented. Also assuming the new line is
# the first one following the initial line of the stmt.
def compute_backslash_indent(self):
self._study2()
assert self.continuation == C_BACKSLASH
str = self.str
i = self.stmt_start
while str[i] in " \t":
i += 1
startpos = i
# See whether the initial line starts an assignment stmt; i.e.,
# look for an = operator
endpos = str.find("\n", startpos) + 1
found = level = 0
while i < endpos:
ch = str[i]
if ch in "([{":
level += 1
i += 1
elif ch in ")]}":
if level:
level -= 1
i += 1
elif ch == '"' or ch == "'":
i = _match_stringre(str, i, endpos).end()
elif ch == "#":
break
elif (
level == 0
and ch == "="
and (i == 0 or str[i - 1] not in "=<>!")
and str[i + 1] != "="
):
found = 1
break
else:
i += 1
if found:
# found a legit =, but it may be the last interesting
# thing on the line
i += 1 # move beyond the =
found = re.match(r"\s*\\", str[i:endpos]) is None
if not found:
# oh well ... settle for moving beyond the first chunk
# of non-whitespace chars
i = startpos
while str[i] not in " \t\n":
i += 1
return len(str[self.stmt_start : i].expandtabs(self.tabwidth)) + 1
# Return the leading whitespace on the initial line of the last
# interesting stmt.
def get_base_indent_string(self):
self._study2()
i, n = self.stmt_start, self.stmt_end
j = i
str = self.str
while j < n and str[j] in " \t":
j += 1
return str[i:j]
# Did the last interesting stmt open a block?
def is_block_opener(self):
self._study2()
return self.lastch == ":"
# Did the last interesting stmt close a block?
def is_block_closer(self):
self._study2()
return _closere(self.str, self.stmt_start) is not None
# index of last open bracket ({[, or None if none
lastopenbracketpos = None
def get_last_open_bracket_pos(self):
self._study2()
return self.lastopenbracketpos
@@ -0,0 +1 @@
# This file denotes the directory as a Python package.