gnulib-tool.py: Implement option --find.

* pygnulib/GLModuleSystem.py (GLModuleSystem.file_is_module): New
method.
(GLModuleSystem.list): Filter the listing in memory; don't use a 'sed'
subprocess.
* gnulib-tool.py (main): Handle mode 'find'.

4 files changed, 97 insertions, 34 deletions

diff --git a/ChangeLog b/ChangeLog
index e259a09333..acb82e903c 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,12 @@
 2022-08-07  Bruno Haible  <bruno@clisp.org>
 
+	gnulib-tool.py: Implement option --find.
+	* pygnulib/GLModuleSystem.py (GLModuleSystem.file_is_module): New
+	method.
+	(GLModuleSystem.list): Filter the listing in memory; don't use a 'sed'
+	subprocess.
+	* gnulib-tool.py (main): Handle mode 'find'.
+
 	gnulib-tool: Fix option --find in combination with option --local-dir.
 	* gnulib-tool (func_prefixed_modules_in_dir): New function.
 	(find): Use it, and filter the directory names away after the 'grep'
diff --git a/gnulib-tool.py b/gnulib-tool.py
index bb763a2245..032deee6e0 100755
--- a/gnulib-tool.py
+++ b/gnulib-tool.py
@@ -43,15 +43,18 @@ import codecs
 import random
 import argparse
 import subprocess as sp
+import shlex
 from tempfile import mktemp
 from pygnulib import constants
 from pygnulib import classes
+from pygnulib import GLError
 
 
 #===============================================================================
 # Define global constants
 #===============================================================================
 APP = constants.APP
+DIRS = constants.DIRS
 ENCS = constants.ENCS
 UTILS = constants.UTILS
 MODES = constants.MODES
@@ -422,6 +425,7 @@ def main():
     # Determine when user tries to combine modes.
     args = [
         cmdargs.mode_list,
+        cmdargs.mode_find,
         cmdargs.mode_import,
         cmdargs.mode_add_import,
         cmdargs.mode_remove_import,
@@ -460,6 +464,9 @@ def main():
     files = None
     if cmdargs.mode_list != None:
         mode = 'list'
+    if cmdargs.mode_find != None:
+        mode = 'find'
+        files = list(cmdargs.non_option_arguments)
     if cmdargs.mode_import != None:
         mode = 'import'
         modules = list(cmdargs.non_option_arguments)
@@ -701,13 +708,64 @@ def main():
     )
 
     # Work in the given mode.
-    if mode in ['list']:
+    if mode == 'list':
         modulesystem = classes.GLModuleSystem(config)
         listing = modulesystem.list()
         result = '\n'.join(listing)
         os.rmdir(config['tempdir'])
         print(result)
 
+    elif mode == 'find':
+        # Prepare GLModuleSystem.find to throw an exception.
+        config.setErrors(True)
+        modulesystem = classes.GLModuleSystem(config)
+        for filename in files:
+            if (isfile(joinpath(DIRS['root'], filename))
+                    or (localpath != None
+                        and any([ isfile(joinpath(localdir, filename))
+                                  for localdir in localpath ]))):
+                # Convert the file name to a POSIX basic regex.
+                # Needs to handle . [ \ * ^ $.
+                filename_regex = filename.replace('\\', '\\\\').replace('[', '\\[').replace('^', '\\^')
+                filename_regex = re.compile('([.*$])').sub('[\\1]', filename_regex)
+                filename_line_regex = '^' + filename_regex + '$'
+                # Read module candidates from gnulib root directory.
+                command = "find modules -type f -print | xargs -n 100 grep -l %s /dev/null | sed -e 's,^modules/,,'" % shlex.quote(filename_line_regex)
+                os.chdir(constants.DIRS['root'])
+                with sp.Popen(command, shell=True, stdout=sp.PIPE) as proc:
+                    result = proc.stdout.read().decode("UTF-8")
+                os.chdir(DIRS['cwd'])
+                # Read module candidates from local directories.
+                if localpath != None and len(localpath) > 0:
+                    command = "find modules -type f -print | xargs -n 100 grep -l %s /dev/null | sed -e 's,^modules/,,' -e 's,\\.diff$,,'" % shlex.quote(filename_line_regex)
+                    for localdir in localpath:
+                        os.chdir(localdir)
+                        with sp.Popen(command, shell=True, stdout=sp.PIPE) as proc:
+                            result += proc.stdout.read().decode("UTF-8")
+                        os.chdir(DIRS['cwd'])
+                listing = [ line
+                            for line in result.split('\n')
+                            if line.strip() ]
+                # Remove modules/ prefix from each file name.
+                pattern = re.compile('^modules/')
+                listing = [ pattern.sub('', line)
+                            for line in listing ]
+                # Filter out undesired file names.
+                listing = [ line
+                            for line in listing
+                            if modulesystem.file_is_module(line) ]
+                module_candidates = sorted(set(listing))
+                for module in module_candidates:
+                    try:
+                        if filename in modulesystem.find(module).getFiles():
+                            print(module)
+                    except GLError:
+                        # Ignore module candidates that don't actually exist.
+                        pass
+            else:
+                message = '%s: warning: file %s does not exist\n' % (constants.APP['name'], filename)
+                sys.stderr.write(message)
+
     elif mode in ['import', 'add-import', 'remove-import', 'update']:
         mode = MODES[mode]
         if not destdir:
diff --git a/gnulib-tool.py.TODO b/gnulib-tool.py.TODO
index 53915662b8..a46da5e2ad 100644
--- a/gnulib-tool.py.TODO
+++ b/gnulib-tool.py.TODO
@@ -20,7 +20,6 @@ Inline all 'sed' invocations.
 --------------------------------------------------------------------------------
 
 Implement the options:
-  --find
   --extract-recursive-dependencies
   --extract-recursive-link-directive
   --extract-tests-module
@@ -37,6 +36,10 @@ Implement the options:
 
 Remove exit() in GLImport.py.
 
+Optimize:
+  - GLModuleSystem: Parse each module description only once.
+  - os.chdir around subprocess creation -> cwd=... argument instead.
+
 --------------------------------------------------------------------------------
 
 commit 76c7703cb2e9e0e803d1296618d8ab9e86e13d6c
diff --git a/pygnulib/GLModuleSystem.py b/pygnulib/GLModuleSystem.py
index 75316515b8..3383b22b28 100644
--- a/pygnulib/GLModuleSystem.py
+++ b/pygnulib/GLModuleSystem.py
@@ -43,6 +43,7 @@ DIRS = constants.DIRS
 ENCS = constants.ENCS
 TESTS = constants.TESTS
 joinpath = constants.joinpath
+subend = constants.subend
 isdir = os.path.isdir
 isfile = os.path.isfile
 filter_filelist = constants.filter_filelist
@@ -113,6 +114,18 @@ class GLModuleSystem(object):
                 sys.stderr.write('gnulib-tool: warning: ')
                 sys.stderr.write('file %s does not exist\n' % str(module))
 
+    def file_is_module(self, filename):
+        '''Given the name of a file in the modules/ directory, return true
+        if should be viewed as a module description file.'''
+        return not (filename == 'ChangeLog' or filename.endswith('/ChangeLog')
+                    or filename == 'COPYING' or filename.endswith('/COPYING')
+                    or filename == 'README' or filename.endswith('/README')
+                    or filename == 'TEMPLATE'
+                    or filename == 'TEMPLATE-EXTENDED'
+                    or filename == 'TEMPLATE-TESTS'
+                    or filename.startswith('.')
+                    or filename.endswith('~'))
+
     def list(self):
         '''GLModuleSystem.list() -> list
 
@@ -123,23 +136,6 @@ class GLModuleSystem(object):
         listing = list()
         localpath = self.config['localpath']
         find_args = ['find', 'modules', '-type', 'f', '-print']
-        sed_args = \
-            [
-                'sed',
-                '-e', r's,^modules/,,',
-                '-e', r'/^ChangeLog$/d',
-                '-e', r'/\/ChangeLog$/d',
-                '-e', r'/^COPYING$/d',
-                '-e', r'/\/COPYING$/d',
-                '-e', r'/^README$/d',
-                '-e', r'/\/README$/d',
-                '-e', r'/^TEMPLATE$/d',
-                '-e', r'/^TEMPLATE-EXTENDED$/d',
-                '-e', r'/^TEMPLATE-TESTS$/d',
-                '-e', r'/^\..*/d',
-                '-e', r'/~$/d',
-                '-e', r'/-tests$/d',
-            ]
 
         # Read modules from gnulib root directory.
         os.chdir(constants.DIRS['root'])
@@ -154,24 +150,23 @@ class GLModuleSystem(object):
                 find = sp.Popen(find_args, stdout=sp.PIPE)
                 result += find.stdout.read().decode("UTF-8")
                 os.chdir(DIRS['cwd'])
-            sed_args += ['-e', r's,\.diff$,,']
-
-        # Save the list of the modules to file.
-        path = joinpath(self.config['tempdir'], 'list')
-        with codecs.open(path, 'wb', 'UTF-8') as file:
-            file.write(result)
-
-        # Filter the list of the modules.
-        stdin = codecs.open(path, 'rb', 'UTF-8')
-        sed = sp.Popen(sed_args, stdin=stdin, stdout=sp.PIPE)
-        result = sed.stdout.read().decode("UTF-8")
-        stdin.close()
-        os.remove(path)
+
         listing = [ line
                     for line in result.split('\n')
                     if line.strip() ]
-        listing = sorted(set(listing))
-        return listing
+        if len(localpath) > 0:
+            listing = [ subend('.diff', '', line)
+                        for line in listing ]
+        # Remove modules/ prefix from each file name.
+        pattern = re.compile('^modules/')
+        listing = [ pattern.sub('', line)
+                    for line in listing ]
+        # Filter out undesired file names.
+        listing = [ line
+                    for line in listing
+                    if self.file_is_module(line) and not line.endswith('-tests') ]
+        modules = sorted(set(listing))
+        return modules
 
 
 #===============================================================================