[LyX master] Adapt lyxpak.py to work with Python 3 on Windows

Enrico Forestieri forenr at lyx.org
Fri Feb 9 21:49:56 UTC 2024


The branch, master, has been updated.

- Log -----------------------------------------------------------------

commit fe99f7b01e6ace4db716326a9d5455b2a168e3fd
Author: Enrico Forestieri <forenr at lyx.org>
Date:   Fri Feb 9 22:46:05 2024 +0100

    Adapt lyxpak.py to work with Python 3 on Windows
    
    Seemingly, the elements of argv on Windows are a different type
    with respect to Linux. A patched version of getopt.py has to be
    used on Windows in order to match variable types.

diff --git a/lib/Makefile.am b/lib/Makefile.am
index d5b0d4441d..efe9cc969e 100644
--- a/lib/Makefile.am
+++ b/lib/Makefile.am
@@ -2746,6 +2746,7 @@ dist_scripts_DATA += \
 	scripts/lyxpaperview.py \
 	scripts/lyxpreview2bitmap.py \
 	scripts/lyxpreview_tools.py \
+	scripts/lyxwin_getopt.py \
 	scripts/lyx_batch.pl.in \
 	scripts/prefs2prefs.py \
 	scripts/prefs2prefs_lfuns.py \
diff --git a/lib/scripts/lyxpak.py b/lib/scripts/lyxpak.py
index 6cdea5c53f..07091f208c 100755
--- a/lib/scripts/lyxpak.py
+++ b/lib/scripts/lyxpak.py
@@ -17,7 +17,6 @@
 
 from __future__ import print_function
 import gzip, os, re, sys
-from getopt import getopt
 from io import BytesIO
 import subprocess
 
@@ -35,6 +34,9 @@ running_on_windows = (os.name == 'nt')
 if running_on_windows:
     from shutil import copyfile
     from tempfile import NamedTemporaryFile
+    from lyxwin_getopt import getopt
+else:
+    from getopt import getopt
 
 # Pre-compiled regular expressions.
 re_lyxfile = re.compile(br"\.lyx$")
@@ -128,7 +130,7 @@ def gather_files(curfile, incfiles, lyx2lyx):
         elif running_on_windows:
             # For some unknown reason, there can be a spurious '\r' in the line
             # separators, causing spurious empty lines when calling splitlines.
-            l2l_stdout = l2l_stdout.replace('\r\r\n', '\r\n')
+            l2l_stdout = l2l_stdout.replace(b'\r\r\n', b'\r\n')
         lines = l2l_stdout.splitlines()
     else:
         input = gzopen(curfile)
@@ -224,7 +226,10 @@ def find_lyx2lyx(progloc, path):
     # for $SOMEDIR/lyx2lyx/lyx2lyx.
     ourpath = os.path.dirname(abspath(progloc))
     (upone, discard) = os.path.split(ourpath)
-    tryit = os.path.join(upone, "lyx2lyx", "lyx2lyx")
+    if running_on_windows:
+        tryit = os.path.join(upone, b"lyx2lyx", b"lyx2lyx")
+    else:
+        tryit = os.path.join(upone, "lyx2lyx", "lyx2lyx")
     if os.access(tryit, os.X_OK):
         return tryit
 
@@ -265,7 +270,10 @@ def main(args):
     ourprog = args[0]
 
     try:
-        (options, argv) = getopt(args[1:], "htzl:o:")
+        if running_on_windows:
+            (options, argv) = getopt(args[1:], b"htzl:o:")
+        else:
+            (options, argv) = getopt(args[1:], "htzl:o:")
     except:
         error(usage(ourprog))
 
@@ -393,7 +401,7 @@ if __name__ == "__main__":
         argv = [argv_unicode[i].encode('utf-8') for i in range(1, argc.value)]
         # Also skip option arguments to the Python interpreter.
         while len(argv) > 0:
-            if not argv[0].startswith("-"):
+            if not argv[0].startswith(b"-"):
                 break
             argv = argv[1:]
         sys.argv = argv
diff --git a/lib/scripts/lyxwin_getopt.py b/lib/scripts/lyxwin_getopt.py
new file mode 100755
index 0000000000..a6f356a084
--- /dev/null
+++ b/lib/scripts/lyxwin_getopt.py
@@ -0,0 +1,217 @@
+# -*- coding: utf-8 -*-
+
+"""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 at iki.fi>.
+#
+# Gerrit Holl <gerrit at nl.linux.org> moved the string-based exceptions
+# to class-based exceptions.
+#
+# Peter Ã…strand <astrand at 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(b'-') and args[0] != '-':
+        if args[0] == '--':
+            args = args[1:]
+            break
+        if args[0].startswith(b'--'):
+            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(b'+'):
+        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(b':', i+1)
+    raise GetoptError(_('option -%s not recognized') % opt, opt)
+
+if __name__ == '__main__':
+    import sys
+    print(getopt(sys.argv[1:], "a:b", ["alpha=", "beta"]))

-----------------------------------------------------------------------

Summary of changes:
 lib/Makefile.am              |   1 +
 lib/scripts/lyxpak.py        |  18 +++-
 lib/scripts/lyxwin_getopt.py | 217 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 231 insertions(+), 5 deletions(-)
 create mode 100755 lib/scripts/lyxwin_getopt.py


hooks/post-receive
-- 
The LyX Source Repository


More information about the lyx-cvs mailing list