summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorStefan Israelsson Tampe <stefan.itampe@gmail.com>2018-08-20 15:02:25 +0200
committerStefan Israelsson Tampe <stefan.itampe@gmail.com>2018-08-20 15:02:25 +0200
commit03f46d99946975e1bd8baccfad4709a3e9d4354d (patch)
treeefa86d9c08f5a3b1d7be77f60677400f8841b841
parentfc3fb780cd2395b58c1b36693d0947bb00ffcae4 (diff)
getopt.py and filecmp.py
-rw-r--r--modules/language/python/compile.scm3
-rw-r--r--modules/language/python/dict.scm15
-rw-r--r--modules/language/python/module/filecmp.py304
-rw-r--r--modules/language/python/module/getopt.py213
4 files changed, 534 insertions, 1 deletions
diff --git a/modules/language/python/compile.scm b/modules/language/python/compile.scm
index 2cef86b..3bf81ef 100644
--- a/modules/language/python/compile.scm
+++ b/modules/language/python/compile.scm
@@ -1021,6 +1021,7 @@
(let ((s (exp vs a)))
(fluid-set! ignore
(cons s (fluid-ref ignore)))
+ (dont-warn s)
s))
((a . b)
@@ -2442,6 +2443,8 @@
(set v x val))
((_ v (#:vecref n) val)
(pylist-set! v n val))
+ ((_ v (#:array-ref n ...) val)
+ (pylist-set! v (list n ...) val))
((_ v (#:vecsub x ...) val)
(pylist-subset! v x ... val))))
diff --git a/modules/language/python/dict.scm b/modules/language/python/dict.scm
index f32b134..4c94f2e 100644
--- a/modules/language/python/dict.scm
+++ b/modules/language/python/dict.scm
@@ -604,7 +604,20 @@
(if (pair? k)
(pylist-set! self (car k) (cdr k))
(raise TypeError
- "wrong type of argument to dict" k)))))))))
+ "wrong type of argument to dict" k))))))
+ ((self . l)
+ (__init__
+ self
+ (let lp ((l l))
+ (match l
+ ((x y . l)
+ (cons (cons (symbol->string
+ (keyword->symbol x))
+ y) (lp l)))
+ (() '())
+ (_ (raise
+ (ValueError
+ "init argument to dict malformed expected key value list"))))))))))
__init__)))
diff --git a/modules/language/python/module/filecmp.py b/modules/language/python/module/filecmp.py
new file mode 100644
index 0000000..57f9851
--- /dev/null
+++ b/modules/language/python/module/filecmp.py
@@ -0,0 +1,304 @@
+module(filecmp)
+
+"""Utilities for comparing files and directories.
+
+Classes:
+ dircmp
+
+Functions:
+ cmp(f1, f2, shallow=True) -> int
+ cmpfiles(a, b, common) -> ([], [], [])
+ clear_cache()
+
+"""
+
+import os
+import stat
+from itertools import filterfalse
+
+__all__ = ['clear_cache', 'cmp', 'dircmp', 'cmpfiles', 'DEFAULT_IGNORES']
+
+_cache = {}
+BUFSIZE = 8*1024
+
+DEFAULT_IGNORES = [
+ 'RCS', 'CVS', 'tags', '.git', '.hg', '.bzr', '_darcs', '__pycache__']
+
+def clear_cache():
+ """Clear the filecmp cache."""
+ _cache.clear()
+
+def cmp(f1, f2, shallow=True):
+ """Compare two files.
+
+ Arguments:
+
+ f1 -- First file name
+
+ f2 -- Second file name
+
+ shallow -- Just check stat signature (do not read the files).
+ defaults to True.
+
+ Return value:
+
+ True if the files are the same, False otherwise.
+
+ This function uses a cache for past comparisons and the results,
+ with cache entries invalidated if their stat information
+ changes. The cache may be cleared by calling clear_cache().
+
+ """
+
+ s1 = _sig(os.stat(f1))
+ s2 = _sig(os.stat(f2))
+ if s1[0] != stat.S_IFREG or s2[0] != stat.S_IFREG:
+ return False
+ if shallow and s1 == s2:
+ return True
+ if s1[1] != s2[1]:
+ return False
+
+ outcome = _cache.get((f1, f2, s1, s2))
+ if outcome is None:
+ outcome = _do_cmp(f1, f2)
+ if len(_cache) > 100: # limit the maximum size of the cache
+ clear_cache()
+ _cache[f1, f2, s1, s2] = outcome
+ return outcome
+
+def _sig(st):
+ return (stat.S_IFMT(st.st_mode),
+ st.st_size,
+ st.st_mtime)
+
+def _do_cmp(f1, f2):
+ bufsize = BUFSIZE
+ with open(f1, 'rb') as fp1, open(f2, 'rb') as fp2:
+ while True:
+ b1 = fp1.read(bufsize)
+ b2 = fp2.read(bufsize)
+ if b1 != b2:
+ return False
+ if not b1:
+ return True
+
+# Directory comparison class.
+#
+class dircmp:
+ """A class that manages the comparison of 2 directories.
+
+ dircmp(a, b, ignore=None, hide=None)
+ A and B are directories.
+ IGNORE is a list of names to ignore,
+ defaults to DEFAULT_IGNORES.
+ HIDE is a list of names to hide,
+ defaults to [os.curdir, os.pardir].
+
+ High level usage:
+ x = dircmp(dir1, dir2)
+ x.report() -> prints a report on the differences between dir1 and dir2
+ or
+ x.report_partial_closure() -> prints report on differences between dir1
+ and dir2, and reports on common immediate subdirectories.
+ x.report_full_closure() -> like report_partial_closure,
+ but fully recursive.
+
+ Attributes:
+ left_list, right_list: The files in dir1 and dir2,
+ filtered by hide and ignore.
+ common: a list of names in both dir1 and dir2.
+ left_only, right_only: names only in dir1, dir2.
+ common_dirs: subdirectories in both dir1 and dir2.
+ common_files: files in both dir1 and dir2.
+ common_funny: names in both dir1 and dir2 where the type differs between
+ dir1 and dir2, or the name is not stat-able.
+ same_files: list of identical files.
+ diff_files: list of filenames which differ.
+ funny_files: list of files which could not be compared.
+ subdirs: a dictionary of dircmp objects, keyed by names in common_dirs.
+ """
+
+ def __init__(self, a, b, ignore=None, hide=None): # Initialize
+ self.left = a
+ self.right = b
+ if hide is None:
+ self.hide = [os.curdir, os.pardir] # Names never to be shown
+ else:
+ self.hide = hide
+ if ignore is None:
+ self.ignore = DEFAULT_IGNORES
+ else:
+ self.ignore = ignore
+
+ def phase0(self): # Compare everything except common subdirectories
+ self.left_list = _filter(os.listdir(self.left),
+ self.hide+self.ignore)
+ self.right_list = _filter(os.listdir(self.right),
+ self.hide+self.ignore)
+ self.left_list.sort()
+ self.right_list.sort()
+
+ def phase1(self): # Compute common names
+ a = dict(zip(map(os.path.normcase, self.left_list), self.left_list))
+ b = dict(zip(map(os.path.normcase, self.right_list), self.right_list))
+ self.common = list(map(a.__getitem__, filter(b.__contains__, a)))
+ self.left_only = list(map(a.__getitem__, filterfalse(b.__contains__, a)))
+ self.right_only = list(map(b.__getitem__, filterfalse(a.__contains__, b)))
+
+ def phase2(self): # Distinguish files, directories, funnies
+ self.common_dirs = []
+ self.common_files = []
+ self.common_funny = []
+
+ for x in self.common:
+ a_path = os.path.join(self.left, x)
+ b_path = os.path.join(self.right, x)
+
+ ok = 1
+ try:
+ a_stat = os.stat(a_path)
+ except OSError as why:
+ # print('Can\'t stat', a_path, ':', why.args[1])
+ ok = 0
+ try:
+ b_stat = os.stat(b_path)
+ except OSError as why:
+ # print('Can\'t stat', b_path, ':', why.args[1])
+ ok = 0
+
+ if ok:
+ a_type = stat.S_IFMT(a_stat.st_mode)
+ b_type = stat.S_IFMT(b_stat.st_mode)
+ if a_type != b_type:
+ self.common_funny.append(x)
+ elif stat.S_ISDIR(a_type):
+ self.common_dirs.append(x)
+ elif stat.S_ISREG(a_type):
+ self.common_files.append(x)
+ else:
+ self.common_funny.append(x)
+ else:
+ self.common_funny.append(x)
+
+ def phase3(self): # Find out differences between common files
+ xx = cmpfiles(self.left, self.right, self.common_files)
+ self.same_files, self.diff_files, self.funny_files = xx
+
+ def phase4(self): # Find out differences between common subdirectories
+ # A new dircmp object is created for each common subdirectory,
+ # these are stored in a dictionary indexed by filename.
+ # The hide and ignore properties are inherited from the parent
+ self.subdirs = {}
+ for x in self.common_dirs:
+ a_x = os.path.join(self.left, x)
+ b_x = os.path.join(self.right, x)
+ self.subdirs[x] = dircmp(a_x, b_x, self.ignore, self.hide)
+
+ def phase4_closure(self): # Recursively call phase4() on subdirectories
+ self.phase4()
+ for sd in self.subdirs.values():
+ sd.phase4_closure()
+
+ def report(self): # Print a report on the differences between a and b
+ # Output format is purposely lousy
+ print('diff', self.left, self.right)
+ if self.left_only:
+ self.left_only.sort()
+ print('Only in', self.left, ':', self.left_only)
+ if self.right_only:
+ self.right_only.sort()
+ print('Only in', self.right, ':', self.right_only)
+ if self.same_files:
+ self.same_files.sort()
+ print('Identical files :', self.same_files)
+ if self.diff_files:
+ self.diff_files.sort()
+ print('Differing files :', self.diff_files)
+ if self.funny_files:
+ self.funny_files.sort()
+ print('Trouble with common files :', self.funny_files)
+ if self.common_dirs:
+ self.common_dirs.sort()
+ print('Common subdirectories :', self.common_dirs)
+ if self.common_funny:
+ self.common_funny.sort()
+ print('Common funny cases :', self.common_funny)
+
+ def report_partial_closure(self): # Print reports on self and on subdirs
+ self.report()
+ for sd in self.subdirs.values():
+ print()
+ sd.report()
+
+ def report_full_closure(self): # Report on self and subdirs recursively
+ self.report()
+ for sd in self.subdirs.values():
+ print()
+ sd.report_full_closure()
+
+ methodmap = dict(subdirs=phase4,
+ same_files=phase3, diff_files=phase3, funny_files=phase3,
+ common_dirs = phase2, common_files=phase2, common_funny=phase2,
+ common=phase1, left_only=phase1, right_only=phase1,
+ left_list=phase0, right_list=phase0)
+
+ def __getattr__(self, attr):
+ if attr not in self.methodmap:
+ raise AttributeError(attr)
+ self.methodmap[attr](self)
+ return getattr(self, attr)
+
+def cmpfiles(a, b, common, shallow=True):
+ """Compare common files in two directories.
+
+ a, b -- directory names
+ common -- list of file names found in both directories
+ shallow -- if true, do comparison based solely on stat() information
+
+ Returns a tuple of three lists:
+ files that compare equal
+ files that are different
+ filenames that aren't regular files.
+
+ """
+ res = ([], [], [])
+ for x in common:
+ ax = os.path.join(a, x)
+ bx = os.path.join(b, x)
+ res[_cmp(ax, bx, shallow)].append(x)
+ return res
+
+
+# Compare two files.
+# Return:
+# 0 for equal
+# 1 for different
+# 2 for funny cases (can't stat, etc.)
+#
+def _cmp(a, b, sh, abs=abs, cmp=cmp):
+ try:
+ return not abs(cmp(a, b, sh))
+ except OSError:
+ return 2
+
+
+# Return a copy with items that occur in skip removed.
+#
+def _filter(flist, skip):
+ return list(filterfalse(skip.__contains__, flist))
+
+
+# Demonstration and testing.
+#
+def demo():
+ import sys
+ import getopt
+ options, args = getopt.getopt(sys.argv[1:], 'r')
+ if len(args) != 2:
+ raise getopt.GetoptError('need exactly two args', None)
+ dd = dircmp(args[0], args[1])
+ if ('-r', '') in options:
+ dd.report_full_closure()
+ else:
+ dd.report()
diff --git a/modules/language/python/module/getopt.py b/modules/language/python/module/getopt.py
new file mode 100644
index 0000000..4474234
--- /dev/null
+++ b/modules/language/python/module/getopt.py
@@ -0,0 +1,213 @@
+module(getopt)
+
+"""Parser for command line options.
+
+This module helps scripts to parse the command line arguments in
+sys.argv. It supports the same conventions as the Unix getopt()
+function (including the special meanings of arguments of the form `-'
+and `--'). Long options similar to those supported by GNU software
+may be used as well via an optional third argument. This module
+provides two functions and an exception:
+
+getopt() -- Parse command line options
+gnu_getopt() -- Like getopt(), but allow option and non-option arguments
+to be intermixed.
+GetoptError -- exception (class) raised with 'opt' attribute, which is the
+option involved with the exception.
+"""
+
+# Long option support added by Lars Wirzenius <liw@iki.fi>.
+#
+# Gerrit Holl <gerrit@nl.linux.org> moved the string-based exceptions
+# to class-based exceptions.
+#
+# Peter Åstrand <astrand@lysator.liu.se> added gnu_getopt().
+#
+# TODO for gnu_getopt():
+#
+# - GNU getopt_long_only mechanism
+# - allow the caller to specify ordering
+# - RETURN_IN_ORDER option
+# - GNU extension with '-' as first character of option string
+# - optional arguments, specified by double colons
+# - an option string with a W followed by semicolon should
+# treat "-W foo" as "--foo"
+
+__all__ = ["GetoptError","error","getopt","gnu_getopt"]
+
+import os
+try:
+ from gettext import gettext as _
+except ImportError:
+ # Bootstrapping Python: gettext's dependencies not built yet
+ def _(s): return s
+
+class GetoptError(Exception):
+ opt = ''
+ msg = ''
+ def __init__(self, msg, opt=''):
+ self.msg = msg
+ self.opt = opt
+ Exception.__init__(self, msg, opt)
+
+ def __str__(self):
+ return self.msg
+
+error = GetoptError # backward compatibility
+
+def getopt(args, shortopts, longopts = []):
+ """getopt(args, options[, long_options]) -> opts, args
+
+ Parses command line options and parameter list. args is the
+ argument list to be parsed, without the leading reference to the
+ running program. Typically, this means "sys.argv[1:]". shortopts
+ is the string of option letters that the script wants to
+ recognize, with options that require an argument followed by a
+ colon (i.e., the same format that Unix getopt() uses). If
+ specified, longopts is a list of strings with the names of the
+ long options which should be supported. The leading '--'
+ characters should not be included in the option name. Options
+ which require an argument should be followed by an equal sign
+ ('=').
+
+ The return value consists of two elements: the first is a list of
+ (option, value) pairs; the second is the list of program arguments
+ left after the option list was stripped (this is a trailing slice
+ of the first argument). Each option-and-value pair returned has
+ the option as its first element, prefixed with a hyphen (e.g.,
+ '-x'), and the option argument as its second element, or an empty
+ string if the option has no argument. The options occur in the
+ list in the same order in which they were found, thus allowing
+ multiple occurrences. Long and short options may be mixed.
+
+ """
+
+ opts = []
+ if type(longopts) == type(""):
+ longopts = [longopts]
+ else:
+ longopts = list(longopts)
+ while args and args[0].startswith('-') and args[0] != '-':
+ if args[0] == '--':
+ args = args[1:]
+ break
+ if args[0].startswith('--'):
+ opts, args = do_longs(opts, args[0][2:], longopts, args[1:])
+ else:
+ opts, args = do_shorts(opts, args[0][1:], shortopts, args[1:])
+
+ return opts, args
+
+def gnu_getopt(args, shortopts, longopts = []):
+ """getopt(args, options[, long_options]) -> opts, args
+
+ This function works like getopt(), except that GNU style scanning
+ mode is used by default. This means that option and non-option
+ arguments may be intermixed. The getopt() function stops
+ processing options as soon as a non-option argument is
+ encountered.
+
+ If the first character of the option string is `+', or if the
+ environment variable POSIXLY_CORRECT is set, then option
+ processing stops as soon as a non-option argument is encountered.
+
+ """
+
+ opts = []
+ prog_args = []
+ if isinstance(longopts, str):
+ longopts = [longopts]
+ else:
+ longopts = list(longopts)
+
+ # Allow options after non-option arguments?
+ if shortopts.startswith('+'):
+ shortopts = shortopts[1:]
+ all_options_first = True
+ elif os.environ.get("POSIXLY_CORRECT"):
+ all_options_first = True
+ else:
+ all_options_first = False
+
+ while args:
+ if args[0] == '--':
+ prog_args += args[1:]
+ break
+
+ if args[0][:2] == '--':
+ opts, args = do_longs(opts, args[0][2:], longopts, args[1:])
+ elif args[0][:1] == '-' and args[0] != '-':
+ opts, args = do_shorts(opts, args[0][1:], shortopts, args[1:])
+ else:
+ if all_options_first:
+ prog_args += args
+ break
+ else:
+ prog_args.append(args[0])
+ args = args[1:]
+
+ return opts, prog_args
+
+def do_longs(opts, opt, longopts, args):
+ try:
+ i = opt.index('=')
+ except ValueError:
+ optarg = None
+ else:
+ opt, optarg = opt[:i], opt[i+1:]
+
+ has_arg, opt = long_has_args(opt, longopts)
+ if has_arg:
+ if optarg is None:
+ if not args:
+ raise GetoptError(_('option --%s requires argument') % opt, opt)
+ optarg, args = args[0], args[1:]
+ elif optarg is not None:
+ raise GetoptError(_('option --%s must not have an argument') % opt, opt)
+ opts.append(('--' + opt, optarg or ''))
+ return opts, args
+
+# Return:
+# has_arg?
+# full option name
+def long_has_args(opt, longopts):
+ possibilities = [o for o in longopts if o.startswith(opt)]
+ if not possibilities:
+ raise GetoptError(_('option --%s not recognized') % opt, opt)
+ # Is there an exact match?
+ if opt in possibilities:
+ return False, opt
+ elif opt + '=' in possibilities:
+ return True, opt
+ # No exact match, so better be unique.
+ if len(possibilities) > 1:
+ # XXX since possibilities contains all valid continuations, might be
+ # nice to work them into the error msg
+ raise GetoptError(_('option --%s not a unique prefix') % opt, opt)
+ assert len(possibilities) == 1
+ unique_match = possibilities[0]
+ has_arg = unique_match.endswith('=')
+ if has_arg:
+ unique_match = unique_match[:-1]
+ return has_arg, unique_match
+
+def do_shorts(opts, optstring, shortopts, args):
+ while optstring != '':
+ opt, optstring = optstring[0], optstring[1:]
+ if short_has_arg(opt, shortopts):
+ if optstring == '':
+ if not args:
+ raise GetoptError(_('option -%s requires argument') % opt,
+ opt)
+ optstring, args = args[0], args[1:]
+ optarg, optstring = optstring, ''
+ else:
+ optarg = ''
+ opts.append(('-' + opt, optarg))
+ return opts, args
+
+def short_has_arg(opt, shortopts):
+ for i in range(len(shortopts)):
+ if opt == shortopts[i] != ':':
+ return shortopts.startswith(':', i+1)
+ raise GetoptError(_('option -%s not recognized') % opt, opt)