diff options
Diffstat (limited to 'modules/language/python/module')
| -rw-r--r-- | modules/language/python/module/#_md5.scm# | 11 | ||||
| -rw-r--r-- | modules/language/python/module/#_sha1.scm# | 10 | ||||
| -rw-r--r-- | modules/language/python/module/#_sha256.scm# | 10 | ||||
| -rw-r--r-- | modules/language/python/module/#bz2.py# | 362 | ||||
| -rw-r--r-- | modules/language/python/module/#difflib.py# | 212 | ||||
| -rw-r--r-- | modules/language/python/module/#json.py# | 369 | ||||
| -rw-r--r-- | modules/language/python/module/#string.scm# | 411 | ||||
| -rw-r--r-- | modules/language/python/module/#textwrap.py# | 479 | ||||
| -rw-r--r-- | modules/language/python/module/xml.py~ | 20 |
9 files changed, 0 insertions, 1884 deletions
diff --git a/modules/language/python/module/#_md5.scm# b/modules/language/python/module/#_md5.scm# deleted file mode 100644 index cc07ebd..0000000 --- a/modules/language/python/module/#_md5.scm# +++ /dev/null @@ -1,11 +0,0 @@ -(define-module (language python module _md5) - #:use-module (language python checksum) - #:use-module (oop pf-objects) - #:export (md5)) - -(define-python-class md5 (Summer) - (define name "md5") - (define digest_size 16) - - (define _command "/usr/bin/md5sum")) - diff --git a/modules/language/python/module/#_sha1.scm# b/modules/language/python/module/#_sha1.scm# deleted file mode 100644 index 87a0adb..0000000 --- a/modules/language/python/module/#_sha1.scm# +++ /dev/null @@ -1,10 +0,0 @@ -(define-module (language python module _sha1) - #:use-module (language python checksum) - #:use-module (oop pf-objects) - #:export (sha1)) - -(define-python-class sha1 (Summer) - (define name "sha1") - (define digest_size 20) - - (define _command "/usr/bin/sha1sum")) diff --git a/modules/language/python/module/#_sha256.scm# b/modules/language/python/module/#_sha256.scm# deleted file mode 100644 index c87ea1a..0000000 --- a/modules/language/python/module/#_sha256.scm# +++ /dev/null @@ -1,10 +0,0 @@ -(define-module (language python module _sha256) - #:use-module (language python checksum) - #:use-module (oop pf-objects) - #:export (sha256)) - -(define-python-class sha256 (Summer) - (define name "sha256") - (define digest_size 32) - - (define _command "/usr/bin/sha256sum")) diff --git a/modules/language/python/module/#bz2.py# b/modules/language/python/module/#bz2.py# deleted file mode 100644 index 3740792..0000000 --- a/modules/language/python/module/#bz2.py# +++ /dev/null @@ -1,362 +0,0 @@ -module(bz2) -"""Interface to the libbzip2 compression library. - -This module provides a file interface, classes for incremental -(de)compression, and functions for one-shot (de)compression. -""" - -__all__ = ["BZ2File", "BZ2Compressor", "BZ2Decompressor", - "open", "compress", "decompress"] - -__author__ = "Nadeem Vawda <nadeem.vawda@gmail.com>" - -from builtins import open as _builtin_open -import io -import os -import warnings -import _compression - -try: - from threading import RLock -except ImportError: - from dummy_threading import RLock - -from _bz2 import BZ2Compressor, BZ2Decompressor - - -_MODE_CLOSED = 0 -_MODE_READ = 1 -# Value 2 no longer used -_MODE_WRITE = 3 - - -class BZ2File(_compression.BaseStream): - - """A file object providing transparent bzip2 (de)compression. - - A BZ2File can act as a wrapper for an existing file object, or refer - directly to a named file on disk. - - Note that BZ2File provides a *binary* file interface - data read is - returned as bytes, and data to be written should be given as bytes. - """ - - def __init__(self, filename, mode="r", buffering=None, compresslevel=9): - """Open a bzip2-compressed file. - - If filename is a str, bytes, or PathLike object, it gives the - name of the file to be opened. Otherwise, it should be a file - object, which will be used to read or write the compressed data. - - mode can be 'r' for reading (default), 'w' for (over)writing, - 'x' for creating exclusively, or 'a' for appending. These can - equivalently be given as 'rb', 'wb', 'xb', and 'ab'. - - buffering is ignored. Its use is deprecated. - - If mode is 'w', 'x' or 'a', compresslevel can be a number between 1 - and 9 specifying the level of compression: 1 produces the least - compression, and 9 (default) produces the most compression. - - If mode is 'r', the input file may be the concatenation of - multiple compressed streams. - """ - # This lock must be recursive, so that BufferedIOBase's - # writelines() does not deadlock. - self._lock = RLock() - self._fp = None - self._closefp = False - self._mode = _MODE_CLOSED - - if buffering is not None: - warnings.warn("Use of 'buffering' argument is deprecated", - DeprecationWarning) - - if not (1 <= compresslevel <= 9): - raise ValueError("compresslevel must be between 1 and 9") - - if mode in ("", "r", "rb"): - mode = "rb" - mode_code = _MODE_READ - elif mode in ("w", "wb"): - mode = "wb" - mode_code = _MODE_WRITE - self._compressor = BZ2Compressor(compresslevel) - elif mode in ("x", "xb"): - mode = "xb" - mode_code = _MODE_WRITE - self._compressor = BZ2Compressor(compresslevel) - elif mode in ("a", "ab"): - mode = "ab" - mode_code = _MODE_WRITE - self._compressor = BZ2Compressor(compresslevel) - else: - raise ValueError("Invalid mode: %r" % (mode,)) - - if isinstance(filename, (str, bytes, os.PathLike)): - self._fp = _builtin_open(filename, mode) - self._closefp = True - self._mode = mode_code - elif hasattr(filename, "read") or hasattr(filename, "write"): - self._fp = filename - self._mode = mode_code - else: - raise TypeError("filename must be a str, bytes, file or PathLike object") - - if self._mode == _MODE_READ: - raw = _compression.DecompressReader(self._fp, - BZ2Decompressor, trailing_error=OSError) - self._buffer = io.BufferedReader(raw) - else: - self._pos = 0 - - def close(self): - """Flush and close the file. - - May be called more than once without error. Once the file is - closed, any other operation on it will raise a ValueError. - """ - with self._lock: - if self._mode == _MODE_CLOSED: - return - try: - if self._mode == _MODE_READ: - self._buffer.close() - elif self._mode == _MODE_WRITE: - self._fp.write(self._compressor.flush()) - self._compressor = None - finally: - try: - if self._closefp: - self._fp.close() - finally: - self._fp = None - self._closefp = False - self._mode = _MODE_CLOSED - self._buffer = None - - @property - def closed(self): - """True if this file is closed.""" - return self._mode == _MODE_CLOSED - - def fileno(self): - """Return the file descriptor for the underlying file.""" - self._check_not_closed() - return self._fp.fileno() - - def seekable(self): - """Return whether the file supports seeking.""" - return self.readable() and self._buffer.seekable() - - def readable(self): - """Return whether the file was opened for reading.""" - self._check_not_closed() - return self._mode == _MODE_READ - - def writable(self): - """Return whether the file was opened for writing.""" - self._check_not_closed() - return self._mode == _MODE_WRITE - - def peek(self, n=0): - """Return buffered data without advancing the file position. - - Always returns at least one byte of data, unless at EOF. - The exact number of bytes returned is unspecified. - """ - with self._lock: - self._check_can_read() - # Relies on the undocumented fact that BufferedReader.peek() - # always returns at least one byte (except at EOF), independent - # of the value of n - return self._buffer.peek(n) - - def read(self, size=-1): - """Read up to size uncompressed bytes from the file. - - If size is negative or omitted, read until EOF is reached. - Returns b'' if the file is already at EOF. - """ - with self._lock: - self._check_can_read() - return self._buffer.read(size) - - def read1(self, size=-1): - """Read up to size uncompressed bytes, while trying to avoid - making multiple reads from the underlying stream. Reads up to a - buffer's worth of data if size is negative. - - Returns b'' if the file is at EOF. - """ - with self._lock: - self._check_can_read() - if size < 0: - size = io.DEFAULT_BUFFER_SIZE - return self._buffer.read1(size) - - def readinto(self, b): - """Read bytes into b. - - Returns the number of bytes read (0 for EOF). - """ - with self._lock: - self._check_can_read() - return self._buffer.readinto(b) - - def readline(self, size=-1): - """Read a line of uncompressed bytes from the file. - - The terminating newline (if present) is retained. If size is - non-negative, no more than size bytes will be read (in which - case the line may be incomplete). Returns b'' if already at EOF. - """ - if not isinstance(size, int): - if not hasattr(size, "__index__"): - raise TypeError("Integer argument expected") - size = size.__index__() - with self._lock: - self._check_can_read() - return self._buffer.readline(size) - - def readlines(self, size=-1): - """Read a list of lines of uncompressed bytes from the file. - - size can be specified to control the number of lines read: no - further lines will be read once the total size of the lines read - so far equals or exceeds size. - """ - if not isinstance(size, int): - if not hasattr(size, "__index__"): - raise TypeError("Integer argument expected") - size = size.__index__() - with self._lock: - self._check_can_read() - return self._buffer.readlines(size) - - def write(self, data): - """Write a byte string to the file. - - Returns the number of uncompressed bytes written, which is - always len(data). Note that due to buffering, the file on disk - may not reflect the data written until close() is called. - """ - with self._lock: - self._check_can_write() - compressed = self._compressor.compress(data) - self._fp.write(compressed) - self._pos += len(data) - return len(data) - - def writelines(self, seq): - """Write a sequence of byte strings to the file. - - Returns the number of uncompressed bytes written. - seq can be any iterable yielding byte strings. - - Line separators are not added between the written byte strings. - """ - with self._lock: - return _compression.BaseStream.writelines(self, seq) - - def seek(self, offset, whence=io.SEEK_SET): - """Change the file position. - - The new position is specified by offset, relative to the - position indicated by whence. Values for whence are: - - 0: start of stream (default); offset must not be negative - 1: current stream position - 2: end of stream; offset must not be positive - - Returns the new file position. - - Note that seeking is emulated, so depending on the parameters, - this operation may be extremely slow. - """ - with self._lock: - self._check_can_seek() - return self._buffer.seek(offset, whence) - - def tell(self): - """Return the current file position.""" - with self._lock: - self._check_not_closed() - if self._mode == _MODE_READ: - return self._buffer.tell() - return self._pos - - -def open(filename, mode="rb", compresslevel=9, - encoding=None, errors=None, newline=None): - """Open a bzip2-compressed file in binary or text mode. - - The filename argument can be an actual filename (a str, bytes, or - PathLike object), or an existing file object to read from or write - to. - - The mode argument can be "r", "rb", "w", "wb", "x", "xb", "a" or - "ab" for binary mode, or "rt", "wt", "xt" or "at" for text mode. - The default mode is "rb", and the default compresslevel is 9. - - For binary mode, this function is equivalent to the BZ2File - constructor: BZ2File(filename, mode, compresslevel). In this case, - the encoding, errors and newline arguments must not be provided. - - For text mode, a BZ2File object is created, and wrapped in an - io.TextIOWrapper instance with the specified encoding, error - handling behavior, and line ending(s). - - """ - if "t" in mode: - if "b" in mode: - raise ValueError("Invalid mode: %r" % (mode,)) - else: - if encoding is not None: - raise ValueError("Argument 'encoding' not supported in binary mode") - if errors is not None: - raise ValueError("Argument 'errors' not supported in binary mode") - if newline is not None: - raise ValueError("Argument 'newline' not supported in binary mode") - - bz_mode = mode.replace("t", "") - binary_file = BZ2File(filename, bz_mode, compresslevel=compresslevel) - - if "t" in mode: - return io.TextIOWrapper(binary_file, encoding, errors, newline) - else: - return binary_file - - -def compress(data, compresslevel=9): - """Compress a block of data. - - compresslevel, if given, must be a number between 1 and 9. - - For incremental compression, use a BZ2Compressor object instead. - """ - comp = BZ2Compressor(compresslevel) - return comp.compress(data) + comp.flush() - - -def decompress(data): - """Decompress a block of data. - - For incremental decompression, use a BZ2Decompressor object instead. - """ - results = [] - while data: - decomp = BZ2Decompressor() - try: - res = decomp.decompress(data) - except OSError: - if results: - break # Leftover data is not a valid bzip2 stream; ignore it. - else: - raise # Error on the first iteration; bail out. - results.append(res) - if not decomp.eof: - raise ValueError("Compressed data ended before the " - "end-of-stream marker was reached") - data = decomp.unused_data - return b"".join(results) diff --git a/modules/language/python/module/#difflib.py# b/modules/language/python/module/#difflib.py# deleted file mode 100644 index a808007..0000000 --- a/modules/language/python/module/#difflib.py# +++ /dev/null @@ -1,212 +0,0 @@ -module(difflib) - -""" -Module difflib -- helpers for computing deltas between objects. - -Function get_close_matches(word, possibilities, n=3, cutoff=0.6): - Use SequenceMatcher to return list of the best "good enough" matches. - -Function context_diff(a, b): - For two lists of strings, return a delta in context diff format. - -Function ndiff(a, b): - Return a delta: the difference between `a` and `b` (lists of strings). - -Function restore(delta, which): - Return one of the two sequences that generated an ndiff delta. - -Function unified_diff(a, b): - For two lists of strings, return a delta in unified diff format. - -Class SequenceMatcher: - A flexible class for comparing pairs of sequences of any type. - -Class Differ: - For producing human-readable deltas from sequences of lines of text. - -Class HtmlDiff: - For producing HTML side by side comparison with change highlights. -""" - -__all__ = ['get_close_matches', 'ndiff', 'restore', 'SequenceMatcher', - 'Differ','IS_CHARACTER_JUNK', 'IS_LINE_JUNK', 'context_diff', - 'unified_diff', 'diff_bytes', 'HtmlDiff', 'Match'] - -from heapq import nlargest as _nlargest -from collections import namedtuple as _namedtuple - -Match = _namedtuple('Match', 'a b size') - -def _calculate_ratio(matches, length): - if length: - return 2.0 * matches / length - return 1.0 - -class SequenceMatcher: - - """ - SequenceMatcher is a flexible class for comparing pairs of sequences of - any type, so long as the sequence elements are hashable. The basic - algorithm predates, and is a little fancier than, an algorithm - published in the late 1980's by Ratcliff and Obershelp under the - hyperbolic name "gestalt pattern matching". The basic idea is to find - the longest contiguous matching subsequence that contains no "junk" - elements (R-O doesn't address junk). The same idea is then applied - recursively to the pieces of the sequences to the left and to the right - of the matching subsequence. This does not yield minimal edit - sequences, but does tend to yield matches that "look right" to people. - - SequenceMatcher tries to compute a "human-friendly diff" between two - sequences. Unlike e.g. UNIX(tm) diff, the fundamental notion is the - longest *contiguous* & junk-free matching subsequence. That's what - catches peoples' eyes. The Windows(tm) windiff has another interesting - notion, pairing up elements that appear uniquely in each sequence. - That, and the method here, appear to yield more intuitive difference - reports than does diff. This method appears to be the least vulnerable - to synching up on blocks of "junk lines", though (like blank lines in - ordinary text files, or maybe "<P>" lines in HTML files). That may be - because this is the only method of the 3 that has a *concept* of - "junk" <wink>. - - Example, comparing two strings, and considering blanks to be "junk": - - >>> s = SequenceMatcher(lambda x: x == " ", - ... "private Thread currentThread;", - ... "private volatile Thread currentThread;") - >>> - - .ratio() returns a float in [0, 1], measuring the "similarity" of the - sequences. As a rule of thumb, a .ratio() value over 0.6 means the - sequences are close matches: - - >>> print(round(s.ratio(), 3)) - 0.866 - >>> - - If you're only interested in where the sequences match, - .get_matching_blocks() is handy: - - >>> for block in s.get_matching_blocks(): - ... print("a[%d] and b[%d] match for %d elements" % block) - a[0] and b[0] match for 8 elements - a[8] and b[17] match for 21 elements - a[29] and b[38] match for 0 elements - - Note that the last tuple returned by .get_matching_blocks() is always a - dummy, (len(a), len(b), 0), and this is the only case in which the last - tuple element (number of elements matched) is 0. - - If you want to know how to change the first sequence into the second, - use .get_opcodes(): - - >>> for opcode in s.get_opcodes(): - ... print("%6s a[%d:%d] b[%d:%d]" % opcode) - equal a[0:8] b[0:8] - insert a[8:8] b[8:17] - equal a[8:29] b[17:38] - - See the Differ class for a fancy human-friendly file differencer, which - uses SequenceMatcher both to compare sequences of lines, and to compare - sequences of characters within similar (near-matching) lines. - - See also function get_close_matches() in this module, which shows how - simple code building on SequenceMatcher can be used to do useful work. - - Timing: Basic R-O is cubic time worst case and quadratic time expected - case. SequenceMatcher is quadratic time for the worst case and has - expected-case behavior dependent in a complicated way on how many - elements the sequences have in common; best case time is linear. - - Methods: - - __init__(isjunk=None, a='', b='') - Construct a SequenceMatcher. - - set_seqs(a, b) - Set the two sequences to be compared. - - set_seq1(a) - Set the first sequence to be compared. - - set_seq2(b) - Set the second sequence to be compared. - - find_longest_match(alo, ahi, blo, bhi) - Find longest matching block in a[alo:ahi] and b[blo:bhi]. - - get_matching_blocks() - Return list of triples describing matching subsequences. - - get_opcodes() - Return list of 5-tuples describing how to turn a into b. - - ratio() - Return a measure of the sequences' similarity (float in [0,1]). - - quick_ratio() - Return an upper bound on .ratio() relatively quickly. - - real_quick_ratio() - Return an upper bound on ratio() very quickly. - """ - - def __init__(self, isjunk=None, a='', b='', autojunk=True): - """Construct a SequenceMatcher. - - Optional arg isjunk is None (the default), or a one-argument - function that takes a sequence element and returns true iff the - element is junk. None is equivalent to passing "lambda x: 0", i.e. - no elements are considered to be junk. For example, pass - lambda x: x in " \\t" - if you're comparing lines as sequences of characters, and don't - want to synch up on blanks or hard tabs. - - Optional arg a is the first of two sequences to be compared. By - default, an empty string. The elements of a must be hashable. See - also .set_seqs() and .set_seq1(). - - Optional arg b is the second of two sequences to be compared. By - default, an empty string. The elements of b must be hashable. See - also .set_seqs() and .set_seq2(). - - Optional arg autojunk should be set to False to disable the - "automatic junk heuristic" that treats popular elements as junk - (see module documentation for more information). - """ - - # Members: - # a - # first sequence - # b - # second sequence; differences are computed as "what do - # we need to do to 'a' to change it into 'b'?" - # b2j - # for x in b, b2j[x] is a list of the indices (into b) - # at which x appears; junk and popular elements do not appear - # fullbcount - # for x in b, fullbcount[x] == the number of times x - # appears in b; only materialized if really needed (used - # only for computing quick_ratio()) - # matching_blocks - # a list of (i, j, k) triples, where a[i:i+k] == b[j:j+k]; - # ascending & non-overlapping in i and in j; terminated by - # a dummy (len(a), len(b), 0) sentinel - # opcodes - # a list of (tag, i1, i2, j1, j2) tuples, where tag is - # one of - # 'replace' a[i1:i2] should be replaced by b[j1:j2] - # 'delete' a[i1:i2] should be deleted - # 'insert' b[j1:j2] should be inserted - # 'equal' a[i1:i2] == b[j1:j2] - # isjunk - # a user-supplied function taking a sequence element and - # returning true iff the element is "junk" -- this has - # subtle but helpful effects on the algorithm, which I'll - # get around to writing up someday <0.9 wink>. - # DON'T USE! Only __chain_b uses this. Use "in self.bjunk". - # bjunk - # the items in b for which isjunk is True. - # bpopular - # nonjunk items in b treated as junk by the heuristic (if used). - - diff --git a/modules/language/python/module/#json.py# b/modules/language/python/module/#json.py# deleted file mode 100644 index 93a7b1c..0000000 --- a/modules/language/python/module/#json.py# +++ /dev/null @@ -1,369 +0,0 @@ -module(json) - -r"""JSON (JavaScript Object Notation) <http://json.org> is a subset of -JavaScript syntax (ECMA-262 3rd edition) used as a lightweight data -interchange format. - -:mod:`json` exposes an API familiar to users of the standard library -:mod:`marshal` and :mod:`pickle` modules. It is derived from a -version of the externally maintained simplejson library. - -Encoding basic Python object hierarchies:: - - >>> import json - >>> json.dumps(['foo', {'bar': ('baz', None, 1.0, 2)}]) - '["foo", {"bar": ["baz", null, 1.0, 2]}]' - >>> print(json.dumps("\"foo\bar")) - "\"foo\bar" - >>> print(json.dumps('\u1234')) - "\u1234" - >>> print(json.dumps('\\')) - "\\" - >>> print(json.dumps({"c": 0, "b": 0, "a": 0}, sort_keys=True)) - {"a": 0, "b": 0, "c": 0} - >>> from io import StringIO - >>> io = StringIO() - >>> json.dump(['streaming API'], io) - >>> io.getvalue() - '["streaming API"]' - -Compact encoding:: - - >>> import json - >>> from collections import OrderedDict - >>> mydict = OrderedDict([('4', 5), ('6', 7)]) - >>> json.dumps([1,2,3,mydict], separators=(',', ':')) - '[1,2,3,{"4":5,"6":7}]' - -Pretty printing:: - - >>> import json - >>> print(json.dumps({'4': 5, '6': 7}, sort_keys=True, indent=4)) - { - "4": 5, - "6": 7 - } - -Decoding JSON:: - - >>> import json - >>> obj = ['foo', {'bar': ['baz', None, 1.0, 2]}] - >>> json.loads('["foo", {"bar":["baz", null, 1.0, 2]}]') == obj - True - >>> json.loads('"\\"foo\\bar"') == '"foo\x08ar' - True - >>> from io import StringIO - >>> io = StringIO('["streaming API"]') - >>> json.load(io)[0] == 'streaming API' - True - -Specializing JSON object decoding:: - - >>> import json - >>> def as_complex(dct): - ... if '__complex__' in dct: - ... return complex(dct['real'], dct['imag']) - ... return dct - ... - >>> json.loads('{"__complex__": true, "real": 1, "imag": 2}', - ... object_hook=as_complex) - (1+2j) - >>> from decimal import Decimal - >>> json.loads('1.1', parse_float=Decimal) == Decimal('1.1') - True - -Specializing JSON object encoding:: - - >>> import json - >>> def encode_complex(obj): - ... if isinstance(obj, complex): - ... return [obj.real, obj.imag] - ... raise TypeError(repr(obj) + " is not JSON serializable") - ... - >>> json.dumps(2 + 1j, default=encode_complex) - '[2.0, 1.0]' - >>> json.JSONEncoder(default=encode_complex).encode(2 + 1j) - '[2.0, 1.0]' - >>> ''.join(json.JSONEncoder(default=encode_complex).iterencode(2 + 1j)) - '[2.0, 1.0]' - - -Using json.tool from the shell to validate and pretty-print:: - - $ echo '{"json":"obj"}' | python -m json.tool - { - "json": "obj" - } - $ echo '{ 1.2:3.4}' | python -m json.tool - Expecting property name enclosed in double quotes: line 1 column 3 (char 2) -""" -__version__ = '2.0.9' -__all__ = [ - 'dump', 'dumps', 'load', 'loads', - 'JSONDecoder', 'JSONDecodeError', 'JSONEncoder', -] - -__author__ = 'Bob Ippolito <bob@redivi.com>' - -from json.decoder import JSONDecoder, JSONDecodeError -from json.encoder import JSONEncoder -import codecs - -_default_encoder = JSONEncoder( - skipkeys=False, - ensure_ascii=True, - check_circular=True, - allow_nan=True, - indent=None, - separators=None, - default=None, -) - -def dump(obj, fp, *, skipkeys=False, ensure_ascii=True, check_circular=True, - allow_nan=True, cls=None, indent=None, separators=None, - default=None, sort_keys=False, **kw): - """Serialize ``obj`` as a JSON formatted stream to ``fp`` (a - ``.write()``-supporting file-like object). - - If ``skipkeys`` is true then ``dict`` keys that are not basic types - (``str``, ``int``, ``float``, ``bool``, ``None``) will be skipped - instead of raising a ``TypeError``. - - If ``ensure_ascii`` is false, then the strings written to ``fp`` can - contain non-ASCII characters if they appear in strings contained in - ``obj``. Otherwise, all such characters are escaped in JSON strings. - - If ``check_circular`` is false, then the circular reference check - for container types will be skipped and a circular reference will - result in an ``OverflowError`` (or worse). - - If ``allow_nan`` is false, then it will be a ``ValueError`` to - serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``) - in strict compliance of the JSON specification, instead of using the - JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``). - - If ``indent`` is a non-negative integer, then JSON array elements and - object members will be pretty-printed with that indent level. An indent - level of 0 will only insert newlines. ``None`` is the most compact - representation. - - If specified, ``separators`` should be an ``(item_separator, key_separator)`` - tuple. The default is ``(', ', ': ')`` if *indent* is ``None`` and - ``(',', ': ')`` otherwise. To get the most compact JSON representation, - you should specify ``(',', ':')`` to eliminate whitespace. - - ``default(obj)`` is a function that should return a serializable version - of obj or raise TypeError. The default simply raises TypeError. - - If *sort_keys* is true (default: ``False``), then the output of - dictionaries will be sorted by key. - - To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the - ``.default()`` method to serialize additional types), specify it with - the ``cls`` kwarg; otherwise ``JSONEncoder`` is used. - - """ - # cached encoder - if (not skipkeys and ensure_ascii and - check_circular and allow_nan and - cls is None and indent is None and separators is None and - default is None and not sort_keys and not kw): - iterable = _default_encoder.iterencode(obj) - else: - if cls is None: - cls = JSONEncoder - iterable = cls(skipkeys=skipkeys, ensure_ascii=ensure_ascii, - check_circular=check_circular, allow_nan=allow_nan, indent=indent, - separators=separators, - default=default, sort_keys=sort_keys, **kw).iterencode(obj) - # could accelerate with writelines in some versions of Python, at - # a debuggability cost - for chunk in iterable: - fp.write(chunk) - - -def dumps(obj, *, skipkeys=False, ensure_ascii=True, check_circular=True, - allow_nan=True, cls=None, indent=None, separators=None, - default=None, sort_keys=False, **kw): - """Serialize ``obj`` to a JSON formatted ``str``. - - If ``skipkeys`` is true then ``dict`` keys that are not basic types - (``str``, ``int``, ``float``, ``bool``, ``None``) will be skipped - instead of raising a ``TypeError``. - - If ``ensure_ascii`` is false, then the return value can contain non-ASCII - characters if they appear in strings contained in ``obj``. Otherwise, all - such characters are escaped in JSON strings. - - If ``check_circular`` is false, then the circular reference check - for container types will be skipped and a circular reference will - result in an ``OverflowError`` (or worse). - - If ``allow_nan`` is false, then it will be a ``ValueError`` to - serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``) in - strict compliance of the JSON specification, instead of using the - JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``). - - If ``indent`` is a non-negative integer, then JSON array elements and - object members will be pretty-printed with that indent level. An indent - level of 0 will only insert newlines. ``None`` is the most compact - representation. - - If specified, ``separators`` should be an ``(item_separator, key_separator)`` - tuple. The default is ``(', ', ': ')`` if *indent* is ``None`` and - ``(',', ': ')`` otherwise. To get the most compact JSON representation, - you should specify ``(',', ':')`` to eliminate whitespace. - - ``default(obj)`` is a function that should return a serializable version - of obj or raise TypeError. The default simply raises TypeError. - - If *sort_keys* is true (default: ``False``), then the output of - dictionaries will be sorted by key. - - To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the - ``.default()`` method to serialize additional types), specify it with - the ``cls`` kwarg; otherwise ``JSONEncoder`` is used. - - """ - # cached encoder - if (not skipkeys and ensure_ascii and - check_circular and allow_nan and - cls is None and indent is None and separators is None and - default is None and not sort_keys and not kw): - return _default_encoder.encode(obj) - if cls is None: - cls = JSONEncoder - return cls( - skipkeys=skipkeys, ensure_ascii=ensure_ascii, - check_circular=check_circular, allow_nan=allow_nan, indent=indent, - separators=separators, default=default, sort_keys=sort_keys, - **kw).encode(obj) - - -_default_decoder = JSONDecoder(object_hook=None, object_pairs_hook=None) - - -def detect_encoding(b): - bstartswith = b.startswith - if bstartswith((codecs.BOM_UTF32_BE, codecs.BOM_UTF32_LE)): - return 'utf-32' - if bstartswith((codecs.BOM_UTF16_BE, codecs.BOM_UTF16_LE)): - return 'utf-16' - if bstartswith(codecs.BOM_UTF8): - return 'utf-8-sig' - - if len(b) >= 4: - if not b[0]: - # 00 00 -- -- - utf-32-be - # 00 XX -- -- - utf-16-be - return 'utf-16-be' if b[1] else 'utf-32-be' - if not b[1]: - # XX 00 00 00 - utf-32-le - # XX 00 00 XX - utf-16-le - # XX 00 XX -- - utf-16-le - return 'utf-16-le' if b[2] or b[3] else 'utf-32-le' - elif len(b) == 2: - if not b[0]: - # 00 XX - utf-16-be - return 'utf-16-be' - if not b[1]: - # XX 00 - utf-16-le - return 'utf-16-le' - # default - return 'utf-8' - - -def load(fp, *, cls=None, object_hook=None, parse_float=None, - parse_int=None, parse_constant=None, object_pairs_hook=None, **kw): - """Deserialize ``fp`` (a ``.read()``-supporting file-like object containing - a JSON document) to a Python object. - - ``object_hook`` is an optional function that will be called with the - result of any object literal decode (a ``dict``). The return value of - ``object_hook`` will be used instead of the ``dict``. This feature - can be used to implement custom decoders (e.g. JSON-RPC class hinting). - - ``object_pairs_hook`` is an optional function that will be called with the - result of any object literal decoded with an ordered list of pairs. The - return value of ``object_pairs_hook`` will be used instead of the ``dict``. - This feature can be used to implement custom decoders that rely on the - order that the key and value pairs are decoded (for example, - collections.OrderedDict will remember the order of insertion). If - ``object_hook`` is also defined, the ``object_pairs_hook`` takes priority. - - To use a custom ``JSONDecoder`` subclass, specify it with the ``cls`` - kwarg; otherwise ``JSONDecoder`` is used. - - """ - return loads(fp.read(), - cls=cls, object_hook=object_hook, - parse_float=parse_float, parse_int=parse_int, - parse_constant=parse_constant, object_pairs_hook=object_pairs_hook, **kw) - - -def loads(s, *, encoding=None, cls=None, object_hook=None, parse_float=None, - parse_int=None, parse_constant=None, object_pairs_hook=None, **kw): - """Deserialize ``s`` (a ``str``, ``bytes`` or ``bytearray`` instance - containing a JSON document) to a Python object. - - ``object_hook`` is an optional function that will be called with the - result of any object literal decode (a ``dict``). The return value of - ``object_hook`` will be used instead of the ``dict``. This feature - can be used to implement custom decoders (e.g. JSON-RPC class hinting). - - ``object_pairs_hook`` is an optional function that will be called with the - result of any object literal decoded with an ordered list of pairs. The - return value of ``object_pairs_hook`` will be used instead of the ``dict``. - This feature can be used to implement custom decoders that rely on the - order that the key and value pairs are decoded (for example, - collections.OrderedDict will remember the order of insertion). If - ``object_hook`` is also defined, the ``object_pairs_hook`` takes priority. - - ``parse_float``, if specified, will be called with the string - of every JSON float to be decoded. By default this is equivalent to - float(num_str). This can be used to use another datatype or parser - for JSON floats (e.g. decimal.Decimal). - - ``parse_int``, if specified, will be called with the string - of every JSON int to be decoded. By default this is equivalent to - int(num_str). This can be used to use another datatype or parser - for JSON integers (e.g. float). - - ``parse_constant``, if specified, will be called with one of the - following strings: -Infinity, Infinity, NaN. - This can be used to raise an exception if invalid JSON numbers - are encountered. - - To use a custom ``JSONDecoder`` subclass, specify it with the ``cls`` - kwarg; otherwise ``JSONDecoder`` is used. - - The ``encoding`` argument is ignored and deprecated. - - """ - if isinstance(s, str): - if s.startswith('\ufeff'): - raise JSONDecodeError("Unexpected UTF-8 BOM (decode using utf-8-sig)", - s, 0) - else: - if not isinstance(s, (bytes, bytearray)): - raise TypeError('the JSON object must be str, bytes or bytearray, ' - 'not {!r}'.format(s.__class__.__name__)) - s = s.decode(detect_encoding(s), 'surrogatepass') - - if (cls is None and object_hook is None and - parse_int is None and parse_float is None and - parse_constant is None and object_pairs_hook is None and not kw): - return _default_decoder.decode(s) - if cls is None: - cls = JSONDecoder - if object_hook is not None: - kw['object_hook'] = object_hook - if object_pairs_hook is not None: - kw['object_pairs_hook'] = object_pairs_hook - if parse_float is not None: - kw['parse_float'] = parse_float - if parse_int is not None: - kw['parse_int'] = parse_int - if parse_constant is not None: - kw['parse_constant'] = parse_constant - return cls(**kw).decode(s) diff --git a/modules/language/python/module/#string.scm# b/modules/language/python/module/#string.scm# deleted file mode 100644 index 3255d99..0000000 --- a/modules/language/python/module/#string.scm# +++ /dev/null @@ -1,411 +0,0 @@ -(define-module (language python module string) - #:use-module (oop pf-objects) - #:use-module (oop goops) - #:use-module (ice-9 match) - #:use-module (language python number) - #:use-module (language python exceptions) - #:use-module (language python yield) - #:use-module (language python list) - #:use-module (language python for) - #:use-module (language python def) - #:use-module (language python string) - #:use-module (language python bytes) - #:use-module ((parser stis-parser) #:select (*whitespace* f-n f-m)) - #:use-module (parser stis-parser lang python3 tool) - #:export (Formatter ascii_letters digits hexdigits)) - -(define digits "0123456789") -(define ascii_letters "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ") -(define hexdigits "0123456789abcdefABCDEF") - -(define (repr x) ((@ (guile) format) #f "~a" x)) -(define int (mk-token (f+ (f-reg! "[0-9]")) string->number)) -(define id (mk-token (f-seq (f-reg! "[_a-zA-Z]") - (f* (f-reg! "[_0-9a-zA-Z]"))))) -(define str (mk-token (f+ (f-not! (f-char #\[))))) - -(define conversion (mk-token (f-reg "[rsa]"))) - -(define fill (mk-token (f-reg! "."))) -(define align (mk-token (f-reg! "[<>=^]"))) -(define sign (mk-token (f-reg! "[-+ ]"))) -(define width int) -(define precision int) -(define type (mk-token (f-reg! "[bcdeEfFgGnosxX%]"))) -(define formatSpec - (f-list - (gg? (f-list #:align (gg? fill) align)) - (gg? sign) - (gg? (mk-token (f-tag! "#"))) - (gg? (mk-token (f-tag! "0"))) - (gg? width) - (gg? (mk-token (f-tag ","))) - (gg? (f-seq "." precision)) - (gg? type))) - -(define (get-align s align width sign) - (define widthq (- width (len sign))) - (define (f s a l) - (match a - ("<" (apply py-ljust (+ sign s) width l)) - (">" (apply py-rjust (+ sign s) width l)) - ("^" (apply py-center (+ sign s) width l)) - ("=" (+ sign (apply py-rjust s widthq l))))) - - (match align - (#f - (f s "<" '())) - ((_ #f a) - (f s a '())) - ((_ fill a) - (f s a (list fill))))) - -(define (convert-string format-str s) - (match (with-fluids ((*whitespace* f-true)) - (stis-parse format-str (f-seq formatSpec f-eof))) - ((align sign sharp zero width comma rec type) - (if width - (get-align s align width "") - s)) - (_ (raise (ValueError (+ "wrong format " format-str)))))) - -(set! (@@ (language python string) format) - (lambda (f s) - (py-format s f))) - -(define (gen-sign s sign) - (let lp ((sign sign)) - (match sign - (#f (lp "-")) - ("+" (if (< s 0) - (values (- s) "-") - (values s "+"))) - ("-" (if (< s 0) - (values (- s) "-") - (values s ""))) - (" " (if (< s 0) - (values (- s) "-") - (values s " ")))))) - -(define (convert-float s format-str) - (match (with-fluids ((*whitespace* f-true)) - (stis-parse format-str (f-seq formatSpec f-eof))) - ((align sign sharp zero width comma prec type) - (call-with-values (lambda () (gen-sign s sign)) - (lambda (s s-sign) - (let* ((prec (if prec prec 6)) - (s (let lp ((type type)) - (match type - (#f (lp "g")) - - ("f" - (format #f (+ "~," (number->string prec) "f") s)) - - ("F" - (let ((s (format #f (+ "~," (number->string prec) - "f") - s))) - (py-replace - (py-replace s "nan" "NAN") - "inf" "INF"))) - - ("e" - (py-replace - (format #f (+ "~," (number->string prec) "e") s) - "E" "e")) - - ("E" - (format #f (+ "~," (number->string prec) "e") s)) - - ("g" - (let ((exp (log10 (abs s)))) - (if (and (<= -4 exp) - (<= exp (max 1 prec))) - (lp "f") - (lp "e")))) - ("G" - (let ((exp (log10 (abs s)))) - (if (and (<= -4 exp) - (<= exp (max 1 prec))) - (lp "F") - (lp "E")))) - ("n" - (let ((exp (log10 (abs s)))) - (if (and (<= -4 exp) - (<= exp (max 1 prec))) - (lp "f") - (format #f (+ "~," (number->string prec) "h") - s)))) - - ("%" - (set s (* s 100)) - (+ (lp "f") "%")))))) - - (if width - (if zero - (get-align s '(#:align "0" "=") width - s-sign) - (get-align s align width - s-sign)) - - (+ s-sign s)))))))) - -(define (convert-complex s format-str) - (match (with-fluids ((*whitespace* f-true)) - (stis-parse format-str (f-seq formatSpec f-eof))) - ((align sign sharp zero width comma prec type) - (let* ((prec (if prec prec 6)) - (s (let lp ((type type)) - (match type - (#f (lp "f")) - ("f" - (format #f (+ "~," (number->string prec) "i") s)))))) - (if width - (get-align s align width "") - s))))) - - -(define-method (py-format (s <real>) f) - (convert-float s f)) -(define-method (py-format (s <py-float>) f) - (convert-float s f)) - -(define-method (py-format (s <complex>) f) - (convert-complex s f)) -(define-method (py-format (s <py-complex>) f) - (convert-complex s f)) - - - - - -(define (convert-integer s format-str) - (match (with-fluids ((*whitespace* f-true)) - (stis-parse format-str (f-seq formatSpec f-eof))) - ((align sign sharp zero width comma prec type) - (call-with-values (lambda () (gen-sign s sign)) - (lambda (s s-sign) - (let ((prefix (if sharp - (match type - ("b" "0b") - ("x" "0x") - ("X" "0X") - ("o" "0o") - ("d" "") - (#f "")) - "")) - (s (let lp ((type type)) - (match type - ("b" - (if comma - (format #f "~:b" s) - (format #f "~b" s))) - ("x" - (if comma - (format #f "~:x" s) - (format #f "~x" s))) - ("X" - (if comma - (format #f "~:@(~:x~)" s) - (format #f "~:@(~x~)" s))) - ("o" - (if comma - (format #f "~:o" s) - (format #f "~o" s))) - ("d" - (if comma - (format #f "~:d" s) - (format #f "~d" s))) - (#f - (lp "d")))))) - (if width - (if zero - (get-align s '(#:align "0" "=") width - (+ s-sign prefix)) - (get-align (+ prefix s) align width - s-sign)) - - (+ s-sign prefix s)))))))) - -(define-method (py-format (s <integer>) f) - (convert-integer s f)) - -(define-method (py-format (o <py-int>) f) - (convert-integer (slot-ref o 'x) f)) - -(define argName (f-or! id int)) -(define attributeName id) -(define elementIndex (f-or! int str)) - -(define fieldName - (f-cons argName (ff* (f-or! (f-list #:attr "." attributeName) - (f-list #:elem "[" elementIndex "]"))))) - -(define (replField fieldName1) - (f-list - #:field - (ff? fieldName1 None) - (ff? (f-seq "!" (mk-token (f-scope conversion))) None) - (ff? (f-seq ":" (mk-token (f-scope formatSpec))) None))) - -(define (tag fieldName1) - (f-seq (f-tag "{") (replField fieldName1) (f-tag "}"))) - -(define nontag (f-list #:str - (mk-token (f+ - (f-or! - (f-tag! "{{") - (f-not! (tag (mk-token - (f-scope - fieldName))))))))) - -(define e (f-seq (ff* (f-or! (tag (mk-token (f-scope fieldName))) - nontag)) - f-eof)) - -(set! (@@ (parser stis-parser lang python3-parser) f-formatter) tag) - -(define mk-gen - (make-generator (l) - (lambda (yield l) - (let lp ((u l) (i 0)) - (match u - (() - (yield "" None None None)) - (((#:str str)) - (yield str None None None)) - (((#:field a b c)) - (if (eq? a None) - (yield "" (number->string i) c b) - (yield "" a b c))) - (((#:field a b c) . u) - (if (eq? a None) - (begin - (yield "" (number->string i) c b) - (lp u (+ i 1))) - (begin - (yield "" a b c) - (lp u i)))) - (((#:str s) (#:field a b c) . u) - (if (eq? a None) - (begin - (yield s (number->string i) c b) - (lp u (+ i 1))) - (begin - (yield s a c b) - (lp u i))))))))) - -(define (f-parse str) - (let ((l (with-fluids ((*whitespace* f-true)) - (parse str e)))) - (mk-gen l))) - -(define stis-parse parse) - -(define-python-class Formatter () - (define format - (lam (self format_string (* args) (** kwargs)) - ((ref self 'vformat) format_string args kwargs))) - - (define vformat2 - (lambda (self fn2 co fo) - (if (and (eq? fo None) (eq? co None)) - ((ref self 'convert_field) fn2 "r") - (let ((fn3 (if (eq? co None) - fn2 - ((ref self 'convert_field) - fn2 co)))) - (if (eq? fo None) - fn3 - ((ref self 'format_field ) fn3 fo)))))) - - (define vformat1 - (lambda (self s fn fo co ss args kwargs) - (if (eq? fn None) - (cons s ss) - (let* ((fn2 ((ref self 'get_field ) fn args kwargs)) - (fn3 (if (and (eq? fo None) (eq? co None)) - ((ref self 'convert_field) fn2 "r") - (let ((fn3 (if (eq? co None) - fn2 - ((ref self 'convert_field) - fn2 co)))) - (if (eq? fo None) - fn3 - ((ref self 'format_field ) - fn3 fo)))))) - (cons* fn3 s ss))))) - - (define vformat - (lambda (self format_string args kwargs) - (set self '_args '()) - (for ((s fn fo co : ((ref self 'parse) format_string))) ((ss '(""))) - (vformat1 self s fn fo co ss args kwargs) - #:final - (begin - ((ref self 'check_unused_args) (ref self '_args) args kwargs) - (apply string-append (reverse ss)))))) - - (define parse - (lambda (self format_string) - (f-parse format_string))) - - (define get_field - (lambda (self field_name args kwargs) - (match (with-fluids ((*whitespace* f-true)) - (stis-parse field_name fieldName)) - ((key a ...) - (set self '_args (cons key (ref self '_args))) - (let ((f ((ref self 'get_value) key args kwargs))) - (let lp ((a a) (f f)) - (match a - (((#:ref r) . l) - (lp l (ref f (string->symbol r)))) - (((#:elem k) . l) - (lp l (pylist-ref f k))) - (() - f))))) - (_ - (throw (TypeError (+ "wrong field name format" field_name))))))) - - (define get_value - (lambda (self key args kwargs) - (set self '__args (cons key args)) - (if (integer? key) - (pylist-ref args key) - (pylist-ref kwargs key)))) - - (define check_unused_args - (lambda (self used_args args kwargs) - (let ((n (len args))) - (let lp ((i 0)) - (if (< i n) - (if (member i used_args) - (lp (+ i 1)) - (warn "unused arg" i))))) - (for ((k v : kwargs)) () - (if (not (member k used_args)) - (warn "unused arg" k))))) - - - (define format_field - (lambda (self value format_spec) - (py-format value format_spec))) - - (define convert_field - (lambda (self value conversion) - (cond - ((equal? conversion "s") - (str value)) - ((equal? conversion "r") - (repr value)) - ((equal? conversion "a") - (ascii value)) - (else - (throw (TypeError (+ "conversion " conversion)))))))) - -(define (ascii x) (bytes x)) - -(define formatter (Formatter)) -(set! (@@ (language python string) formatter) formatter) -(set! (@@ (language python compile) formatter) (ref formatter 'vformat2)) diff --git a/modules/language/python/module/#textwrap.py# b/modules/language/python/module/#textwrap.py# deleted file mode 100644 index 150e3f9..0000000 --- a/modules/language/python/module/#textwrap.py# +++ /dev/null @@ -1,479 +0,0 @@ -module(textwrap) - -"""Text wrapping and filling. -""" - -# Copyright (C) 1999-2001 Gregory P. Ward. -# Copyright (C) 2002, 2003 Python Software Foundation. -# Written by Greg Ward <gward@python.net> - -import re - -__all__ = ['wrap', 'TextWrapper', 'fill', 'dedent', 'indent', 'shorten'] - -# Hardcode the recognized whitespace characters to the US-ASCII -# whitespace characters. The main reason for doing this is that -# some Unicode spaces (like \u00a0) are non-breaking whitespaces. -_whitespace = '\t\n\x0b\x0c\r ' - - -class TextWrapper: - """ - Object for wrapping/filling text. The public interface consists of - the wrap() and fill() methods; the other methods are just there for - subclasses to override in order to tweak the default behaviour. - If you want to completely replace the main wrapping algorithm, - you'll probably have to override _wrap_chunks(). - - Several instance attributes control various aspects of wrapping: - width (default: 70) - the maximum width of wrapped lines (unless break_long_words - is false) - initial_indent (default: "") - string that will be prepended to the first line of wrapped - output. Counts towards the line's width. - subsequent_indent (default: "") - string that will be prepended to all lines save the first - of wrapped output; also counts towards each line's width. - expand_tabs (default: true) - Expand tabs in input text to spaces before further processing. - Each tab will become 0 .. 'tabsize' spaces, depending on its position - in its line. If false, each tab is treated as a single character. - tabsize (default: 8) - Expand tabs in input text to 0 .. 'tabsize' spaces, unless - 'expand_tabs' is false. - replace_whitespace (default: true) - Replace all whitespace characters in the input text by spaces - after tab expansion. Note that if expand_tabs is false and - replace_whitespace is true, every tab will be converted to a - single space! - fix_sentence_endings (default: false) - Ensure that sentence-ending punctuation is always followed - by two spaces. Off by default because the algorithm is - (unavoidably) imperfect. - break_long_words (default: true) - Break words longer than 'width'. If false, those words will not - be broken, and some lines might be longer than 'width'. - break_on_hyphens (default: true) - Allow breaking hyphenated words. If true, wrapping will occur - preferably on whitespaces and right after hyphens part of - compound words. - drop_whitespace (default: true) - Drop leading and trailing whitespace from lines. - max_lines (default: None) - Truncate wrapped lines. - placeholder (default: ' [...]') - Append to the last line of truncated text. - """ - - unicode_whitespace_trans = {} - uspace = ord(' ') - for x in _whitespace: - unicode_whitespace_trans[ord(x)] = uspace - - # This funky little regex is just the trick for splitting - # text up into word-wrappable chunks. E.g. - # "Hello there -- you goof-ball, use the -b option!" - # splits into - # Hello/ /there/ /--/ /you/ /goof-/ball,/ /use/ /the/ /-b/ /option! - # (after stripping out empty strings). - word_punct = r'[\w!"\'&.,?]' - letter = r'[^\d\W]' - whitespace = r'[%s]' % re.escape(_whitespace) - nowhitespace = '[^' + whitespace[1:] - wordsep_re = re.compile(r''' - ( # any whitespace - %(ws)s+ - | # em-dash between words - (?<=%(wp)s) -{2,} (?=\w) - | # word, possibly hyphenated - %(nws)s+? (?: - # hyphenated word - -(?: (?<=%(lt)s{2}-) | (?<=%(lt)s-%(lt)s-)) - (?= %(lt)s -? %(lt)s) - | # end of word - (?=%(ws)s|\Z) - | # em-dash - (?<=%(wp)s) (?=-{2,}\w) - ) - )''' % {'wp': word_punct, 'lt': letter, - 'ws': whitespace, 'nws': nowhitespace}, - re.VERBOSE) - del word_punct, letter, nowhitespace - - # This less funky little regex just split on recognized spaces. E.g. - # "Hello there -- you goof-ball, use the -b option!" - # splits into - # Hello/ /there/ /--/ /you/ /goof-ball,/ /use/ /the/ /-b/ /option!/ - wordsep_simple_re = re.compile(r'(%s+)' % whitespace) - del whitespace - - # XXX this is not locale- or charset-aware -- string.lowercase - # is US-ASCII only (and therefore English-only) - sentence_end_re = re.compile(r'[a-z]' # lowercase letter - r'[\.\!\?]' # sentence-ending punct. - r'[\"\']?' # optional end-of-quote - r'\Z') # end of chunk - - def __init__(self, - width=70, - initial_indent="", - subsequent_indent="", - expand_tabs=True, - replace_whitespace=True, - fix_sentence_endings=False, - break_long_words=True, - drop_whitespace=True, - break_on_hyphens=True, - tabsize=8, - *, - max_lines=None, - placeholder=' [...]'): - self.width = width - self.initial_indent = initial_indent - self.subsequent_indent = subsequent_indent - self.expand_tabs = expand_tabs - self.replace_whitespace = replace_whitespace - self.fix_sentence_endings = fix_sentence_endings - self.break_long_words = break_long_words - self.drop_whitespace = drop_whitespace - self.break_on_hyphens = break_on_hyphens - self.tabsize = tabsize - self.max_lines = max_lines - self.placeholder = placeholder - - - # -- Private methods ----------------------------------------------- - # (possibly useful for subclasses to override) - - def _munge_whitespace(self, text): - """_munge_whitespace(text : string) -> string - - Munge whitespace in text: expand tabs and convert all other - whitespace characters to spaces. Eg. " foo\\tbar\\n\\nbaz" - becomes " foo bar baz". - """ - if self.expand_tabs: - text = text.expandtabs(self.tabsize) - if self.replace_whitespace: - text = text.translate(self.unicode_whitespace_trans) - return text - - - def _split(self, text): - """_split(text : string) -> [string] - - Split the text to wrap into indivisible chunks. Chunks are - not quite the same as words; see _wrap_chunks() for full - details. As an example, the text - Look, goof-ball -- use the -b option! - breaks into the following chunks: - 'Look,', ' ', 'goof-', 'ball', ' ', '--', ' ', - 'use', ' ', 'the', ' ', '-b', ' ', 'option!' - if break_on_hyphens is True, or in: - 'Look,', ' ', 'goof-ball', ' ', '--', ' ', - 'use', ' ', 'the', ' ', '-b', ' ', option!' - otherwise. - """ - if self.break_on_hyphens is True: - chunks = self.wordsep_re.split(text) - else: - chunks = self.wordsep_simple_re.split(text) - chunks = [c for c in chunks if c] - return chunks - - def _fix_sentence_endings(self, chunks): - """_fix_sentence_endings(chunks : [string]) - - Correct for sentence endings buried in 'chunks'. Eg. when the - original text contains "... foo.\\nBar ...", munge_whitespace() - and split() will convert that to [..., "foo.", " ", "Bar", ...] - which has one too few spaces; this method simply changes the one - space to two. - """ - i = 0 - patsearch = self.sentence_end_re.search - while i < len(chunks)-1: - if chunks[i+1] == " " and patsearch(chunks[i]): - chunks[i+1] = " " - i += 2 - else: - i += 1 - - def _handle_long_word(self, reversed_chunks, cur_line, cur_len, width): - """_handle_long_word(chunks : [string], - cur_line : [string], - cur_len : int, width : int) - - Handle a chunk of text (most likely a word, not whitespace) that - is too long to fit in any line. - """ - # Figure out when indent is larger than the specified width, and make - # sure at least one character is stripped off on every pass - if width < 1: - space_left = 1 - else: - space_left = width - cur_len - - # If we're allowed to break long words, then do so: put as much - # of the next chunk onto the current line as will fit. - if self.break_long_words: - cur_line.append(reversed_chunks[-1][:space_left]) - reversed_chunks[-1] = reversed_chunks[-1][space_left:] - - # Otherwise, we have to preserve the long word intact. Only add - # it to the current line if there's nothing already there -- - # that minimizes how much we violate the width constraint. - elif not cur_line: - cur_line.append(reversed_chunks.pop()) - - # If we're not allowed to break long words, and there's already - # text on the current line, do nothing. Next time through the - # main loop of _wrap_chunks(), we'll wind up here again, but - # cur_len will be zero, so the next line will be entirely - # devoted to the long word that we can't handle right now. - - def _wrap_chunks(self, chunks): - """_wrap_chunks(chunks : [string]) -> [string] - - Wrap a sequence of text chunks and return a list of lines of - length 'self.width' or less. (If 'break_long_words' is false, - some lines may be longer than this.) Chunks correspond roughly - to words and the whitespace between them: each chunk is - indivisible (modulo 'break_long_words'), but a line break can - come between any two chunks. Chunks should not have internal - whitespace; ie. a chunk is either all whitespace or a "word". - Whitespace chunks will be removed from the beginning and end of - lines, but apart from that whitespace is preserved. - """ - lines = [] - if self.width <= 0: - raise ValueError("invalid width %r (must be > 0)" % self.width) - if self.max_lines is not None: - if self.max_lines > 1: - indent = self.subsequent_indent - else: - indent = self.initial_indent - if len(indent) + len(self.placeholder.lstrip()) > self.width: - raise ValueError("placeholder too large for max width") - - # Arrange in reverse order so items can be efficiently popped - # from a stack of chucks. - chunks.reverse() - - while chunks: - # Start the list of chunks that will make up the current line. - # cur_len is just the length of all the chunks in cur_line. - cur_line = [] - cur_len = 0 - - # Figure out which static string will prefix this line. - if lines: - indent = self.subsequent_indent - else: - indent = self.initial_indent - - # Maximum width for this line. - width = self.width - len(indent) - - # First chunk on line is whitespace -- drop it, unless this - # is the very beginning of the text (ie. no lines started yet). - if self.drop_whitespace and chunks[-1].strip() == '' and lines: - del chunks[-1] - - while chunks: - l = len(chunks[-1]) - - # Can at least squeeze this chunk onto the current line. - if cur_len + l <= width: - cur_line.append(chunks.pop()) - cur_len += l - - # Nope, this line is full. - else: - break - - # The current line is full, and the next chunk is too big to - # fit on *any* line (not just this one). - if chunks and len(chunks[-1]) > width: - self._handle_long_word(chunks, cur_line, cur_len, width) - cur_len = sum(map(len, cur_line)) - - # If the last chunk on this line is all whitespace, drop it. - if self.drop_whitespace and cur_line and cur_line[-1].strip() == '': - cur_len -= len(cur_line[-1]) - del cur_line[-1] - - if cur_line: - if (self.max_lines is None or - len(lines) + 1 < self.max_lines or - (not chunks or - self.drop_whitespace and - len(chunks) == 1 and - not chunks[0].strip()) and cur_len <= width): - # Convert current line back to a string and store it in - # list of all lines (return value). - lines.append(indent + ''.join(cur_line)) - else: - while cur_line: - if (cur_line[-1].strip() and - cur_len + len(self.placeholder) <= width): - cur_line.append(self.placeholder) - lines.append(indent + ''.join(cur_line)) - break - cur_len -= len(cur_line[-1]) - del cur_line[-1] - else: - if lines: - prev_line = lines[-1].rstrip() - if (len(prev_line) + len(self.placeholder) <= - self.width): - lines[-1] = prev_line + self.placeholder - break - lines.append(indent + self.placeholder.lstrip()) - break - return lines - - def _split_chunks(self, text): - text = self._munge_whitespace(text) - return self._split(text) - - # -- Public interface ---------------------------------------------- - - def wrap(self, text): - """wrap(text : string) -> [string] - - Reformat the single paragraph in 'text' so it fits in lines of - no more than 'self.width' columns, and return a list of wrapped - lines. Tabs in 'text' are expanded with string.expandtabs(), - and all other whitespace characters (including newline) are - converted to space. - """ - chunks = self._split_chunks(text) - - if self.fix_sentence_endings: - self._fix_sentence_endings(chunks) - - return self._wrap_chunks(chunks) - - def fill(self, text): - """fill(text : string) -> string - - Reformat the single paragraph in 'text' to fit in lines of no - more than 'self.width' columns, and return a new string - containing the entire wrapped paragraph. - """ - return "\n".join(self.wrap(text)) - -# -- Convenience interface --------------------------------------------- - -def wrap(text, width=70, **kwargs): - """Wrap a single paragraph of text, returning a list of wrapped lines. - - Reformat the single paragraph in 'text' so it fits in lines of no - more than 'width' columns, and return a list of wrapped lines. By - default, tabs in 'text' are expanded with string.expandtabs(), and - all other whitespace characters (including newline) are converted to - space. See TextWrapper class for available keyword args to customize - wrapping behaviour. - """ - w = TextWrapper(width=width, **kwargs) - return w.wrap(text) - -def fill(text, width=70, **kwargs): - """Fill a single paragraph of text, returning a new string. - - Reformat the single paragraph in 'text' to fit in lines of no more - than 'width' columns, and return a new string containing the entire - wrapped paragraph. As with wrap(), tabs are expanded and other - whitespace characters converted to space. See TextWrapper class for - available keyword args to customize wrapping behaviour. - """ - w = TextWrapper(width=width, **kwargs) - return w.fill(text) - -def shorten(text, width, **kwargs): - """Collapse and truncate the given text to fit in the given width. - - The text first has its whitespace collapsed. If it then fits in - the *width*, it is returned as is. Otherwise, as many words - as possible are joined and then the placeholder is appended:: - - >>> textwrap.shorten("Hello world!", width=12) - 'Hello world!' - >>> textwrap.shorten("Hello world!", width=11) - 'Hello [...]' - """ - w = TextWrapper(width=width, max_lines=1, **kwargs) - return w.fill(' '.join(text.strip().split())) - -# -- Loosely related functionality ------------------------------------- - -_whitespace_only_re = re.compile('^[ \t]+$', re.MULTILINE) -_leading_whitespace_re = re.compile('(^[ \t]*)(?:[^ \t\n])', re.MULTILINE) - -def dedent(text): - """Remove any common leading whitespace from every line in `text`. - - This can be used to make triple-quoted strings line up with the left - edge of the display, while still presenting them in the source code - in indented form. - - Note that tabs and spaces are both treated as whitespace, but they - are not equal: the lines " hello" and "\\thello" are - considered to have no common leading whitespace. (This behaviour is - new in Python 2.5; older versions of this module incorrectly - expanded tabs before searching for common leading whitespace.) - """ - # Look for the longest leading string of spaces and tabs common to - # all lines. - margin = None - text = _whitespace_only_re.sub('', text) - indents = _leading_whitespace_re.findall(text) - - for indent in indents: - if margin is None: - margin = indent - - # Current line more deeply indented than previous winner: - # no change (previous winner is still on top). - elif indent.startswith(margin): - pass - - # Current line consistent with and no deeper than previous winner: - # it's the new winner. - elif margin.startswith(indent): - margin = indent - - - # Find the largest common whitespace between current line and previous - # winner. - else: - for i, (x, y) in enumerate(zip(margin, indent)): - if x != y: - margin = margin[:i] - break - else: - margin = margin[:len(indent)] - - if margin: - text = re.sub(r'(?m)^' + margin, '', text) - return text - - -def indent(text, prefix, predicate=None): - """Adds 'prefix' to the beginning of selected lines in 'text'. - - If 'predicate' is provided, 'prefix' will only be added to the lines - where 'predicate(line)' is True. If 'predicate' is not provided, - it will default to adding 'prefix' to all non-empty lines that do not - consist solely of whitespace characters. - """ - if predicate is None: - def predicate(line): - return line.strip() - - def prefixed_lines(): - for line in text.splitlines(True): - yield (prefix + line if predicate(line) else line) - return ''.join(prefixed_lines()) diff --git a/modules/language/python/module/xml.py~ b/modules/language/python/module/xml.py~ deleted file mode 100644 index bf6d8dd..0000000 --- a/modules/language/python/module/xml.py~ +++ /dev/null @@ -1,20 +0,0 @@ -"""Core XML support for Python. - -This package contains four sub-packages: - -dom -- The W3C Document Object Model. This supports DOM Level 1 + - Namespaces. - -parsers -- Python wrappers for XML parsers (currently only supports Expat). - -sax -- The Simple API for XML, developed by XML-Dev, led by David - Megginson and ported to Python by Lars Marius Garshol. This - supports the SAX 2 API. - -etree -- The ElementTree XML library. This is a subset of the full - ElementTree XML release. - -""" - - -__all__ = ["dom", "parsers", "sax", "etree"] |