Merge pull request #2262 from bcoca/find_regex

added regex support to find

files/find.py

@@ -25,8 +25,6 @@ import stat
 import fnmatch
 import time
 import re
-import shutil
-
 
 DOCUMENTATION = '''
 ---
@@ -50,17 +48,18 @@ options:
         required: false
         default: '*'
         description:
-            - One or more (shell type) file glob patterns, which restrict the list of files to be returned to
+            - One or more (shell or regex) patterns, which type is controled by C(use_regex) option.
-              those whose basenames match at least one of the patterns specified.  Multiple patterns can be
+            - The patterns restrict the list of files to be returned to those whose basenames match at
-              specified using a list.
+              least one of the patterns specified. Multiple patterns can be specified using a list.
+        aliases: ['pattern']
     contains:
         required: false
         default: null
         description:
-            - One or more re patterns which should be matched against the file content 
+            - One or more re patterns which should be matched against the file content
     paths:
         required: true
-        aliases: [ "name" ]
+        aliases: [ "name", "path" ]
         description:
             - List of paths to the file or directory to search. All paths must be fully qualified.
     file_type:
@@ -108,6 +107,12 @@ options:
         choices: [ True, False ]
         description:
             - Set this to true to retrieve a file's sha1 checksum
+    use_regex:
+        required: false
+        default: "False"
+        choices: [ True, False ]
+        description:
+            - If false the patterns are file globs (shell) if true they are python regexes
 '''
 
 
@@ -121,8 +126,11 @@ EXAMPLES = '''
 # Recursively find /var/tmp files with last access time greater than 3600 seconds
 - find: paths="/var/tmp" age="3600" age_stamp=atime recurse=yes
 
-# find /var/log files equal or greater than 10 megabytes ending with .log or .log.gz
+# find /var/log files equal or greater than 10 megabytes ending with .old or .log.gz
-- find: paths="/var/tmp" patterns="*.log","*.log.gz" size="10m"
+- find: paths="/var/tmp" patterns="'*.old','*.log.gz'" size="10m"
+
+# find /var/log files equal or greater than 10 megabytes ending with .old or .log.gz via regex
+- find: paths="/var/tmp" patterns="^.*?\.(?:old|log\.gz)$" size="10m" use_regex=True
 '''
 
 RETURN = '''
@@ -152,13 +160,23 @@ examined:
     sample: 34
 '''
 
-def pfilter(f, patterns=None):
+def pfilter(f, patterns=None, use_regex=False):
     '''filter using glob patterns'''
+
     if patterns is None:
         return True
-    for p in patterns:
+
-        if fnmatch.fnmatch(f, p):
+    if use_regex:
-             return True
+        for p in patterns:
+            r =  re.compile(p)
+            if r.match(f):
+                return True
+    else:
+
+        for p in patterns:
+            if fnmatch.fnmatch(f, p):
+                return True
+
     return False
 
 
@@ -236,8 +254,8 @@ def statinfo(st):
 def main():
     module = AnsibleModule(
         argument_spec = dict(
-            paths         = dict(required=True, aliases=['name'], type='list'),
+            paths         = dict(required=True, aliases=['name','path'], type='list'),
-            patterns      = dict(default=['*'], type='list'),
+            patterns      = dict(default=['*'], type='list', aliases=['pattern']),
             contains      = dict(default=None, type='str'),
             file_type     = dict(default="file", choices=['file', 'directory'], type='str'),
             age           = dict(default=None, type='str'),
@@ -247,6 +265,7 @@ def main():
             hidden        = dict(default="False", type='bool'),
             follow        = dict(default="False", type='bool'),
             get_checksum  = dict(default="False", type='bool'),
+            use_regex     = dict(default="False", type='bool'),
         ),
     )
 
@@ -292,16 +311,21 @@ def main():
                     if os.path.basename(fsname).startswith('.') and not params['hidden']:
                        continue
 
-                    st = os.stat(fsname)
+                    try:
+                        st = os.stat(fsname)
+                    except:
+                        msg+="%s was skipped as it does not seem to be a valid file or it cannot be accessed\n" % fsname
+                        continue
+
                     r = {'path': fsname}
                     if stat.S_ISDIR(st.st_mode) and params['file_type'] == 'directory':
-                        if pfilter(fsobj, params['patterns']) and agefilter(st, now, age, params['age_stamp']):
+                        if pfilter(fsobj, params['patterns'], params['use_regex']) and agefilter(st, now, age, params['age_stamp']):
 
                             r.update(statinfo(st))
                             filelist.append(r)
 
                     elif stat.S_ISREG(st.st_mode) and params['file_type'] == 'file':
-                        if pfilter(fsobj, params['patterns']) and \
+                        if pfilter(fsobj, params['patterns'], params['use_regex']) and \
                            agefilter(st, now, age, params['age_stamp']) and \
                            sizefilter(st, size) and \
                            contentfilter(fsname, params['contains']):
@@ -314,7 +338,7 @@ def main():
                 if not params['recurse']:
                     break
         else:
-            msg+="%s was skipped as it does not seem to be a valid directory or it cannot be accessed\n"
+            msg+="%s was skipped as it does not seem to be a valid directory or it cannot be accessed\n" % npath
 
     matched = len(filelist)
     module.exit_json(files=filelist, changed=False, msg=msg, matched=matched, examined=looked)