Using wildcard for "if .... in .." statement

Question

I am trying to find files in directories where the file name used is sometimes only a part of the full file name.

So

check_meta=os.listdir(currentPath)

gives

['ANZMeta.xsl', 'Benefited_Areas', 'divisons', 'emergency', 'Error_LOG.txt', 'hex.dbf', 'hex.shp', 'hex.shp_BaseMetadata.xml', 'hex.shx', 'Maintenance_Areas', 'Rates.mxd', 'Regulated_Parking', 'schema.ini', 'Service_Areas', 'Shortcut to Local_Govt.lnk', 'TAB', 'TRC.rar', 'trc_boundary.dbf', 'trc_boundary.kml', 'trc_boundary.prj', 'trc_boundary.sbn', 'trc_boundary.sbx', 'trc_boundary.shp', 'trc_boundary.shp.ATGIS29.1772.3444.sr.lock', 'trc_boundary.shp.ATGIS30.2668.2356.sr.lock', 'trc_boundary.shp.xml', 'trc_boundary.shx', 'trc_boundary_Metadata.xml.auto', 'trc_boundary_Polygon.dbf', 'trc_boundary_Polygon.prj', 'trc_boundary_Polygon.sbn', 'trc_boundary_Polygon.sbx', 'trc_boundary_Polygon.shp', 'trc_boundary_Polygon.shp.ATGIS29.1772.3444.sr.lock', 'trc_boundary_Polygon.shx', 'trc_boundary_polygon.xml', 'Urbanlevy_bdy_region.dbf', 'Urbanlevy_bdy_region.prj', 'Urbanlevy_bdy_region.shp', 'Urbanlevy_bdy_region.shp.xml', 'Urbanlevy_bdy_region.shx', 'Urbanlevy_bdy_trc.dbf', 'Urbanlevy_bdy_trc. prj', 'Urbanlevy_bdy_trc.sbn', 'Urbanlevy_bdy_trc.sbx', 'Urbanlevy_bdy_trc.shp', 'Urbanlevy_bdy_trc.shp.xml', 'Urbanlevy_bdy_trc.shx']

I want to

existingXML=FileNm[:FileNm.find('.')]
if  existingXML+"*"+'.xml' in check_meta: # this is where the issue is
   print "exists"

so sometimes the xml to use is Urbanlevy_bdy_trc.shp.xml and at others it is Urbanlevy_bdy_trc.xml (whichever exists -note it is not to simply use a OR function for ".shp.xml" as there are multiple file extentions like tab, ecw etc that the datasets will have). Also sometimes the related xml file maybe called Urbanlevy_bdy_trc_Metadata.shp.xml so the key is just to search for the core file name "Urbanlevy_bdy_trc" with extension .xml

How can I specify this? the purpose of this is mentioned in Search and replace multiple lines in xml/text files using python

FULL CODE

import os, xml, arcpy, shutil, datetime
from xml.etree import ElementTree as et 

path=os.getcwd()
RootDirectory=path
arcpy.env.workspace = path
Count=0

Generated_XMLs=RootDirectory+'\GeneratedXML_LOG.txt'
f = open(Generated_XMLs, 'a')
f.write("Log of Metadata Creation Process - Update: "+str(datetime.datetime.now())+"\n")
f.close()

for root, dirs, files in os.walk(RootDirectory, topdown=False):
    #print root, dirs
    for directory in dirs:
        currentPath=os.path.join(root,directory)
        os.chdir(currentPath)
        arcpy.env.workspace = currentPath
        print currentPath
#def Create_xml(currentPath):

        FileList = arcpy.ListFeatureClasses()
        zone="_Zone"

        for File in FileList:
            Count+=1
            FileDesc_obj = arcpy.Describe(File)
            FileNm=FileDesc_obj.file
            print FileNm

            check_meta=os.listdir(currentPath)
            existingXML=FileNm[:FileNm.find('.')]
            print "XML: "+existingXML
            print check_meta
            #if  existingXML+'.xml' in check_meta:
            if any(f.startswith(existingXML) and f.endswith('.xml') for f in check_meta):
                print "exists"
                newMetaFile=FileNm+"_2012Metadata.xml"
                shutil.copy2(FileNm+'.xml', newMetaFile)
            else:
                print "Does not exist"
                newMetaFile=FileNm+"_BaseMetadata.xml"
                shutil.copy2('L:\Data_Admin\QA\Metadata_python_toolset\Master_Metadata.xml', newMetaFile)
            tree=et.parse(newMetaFile)

            print "Processing: "+str(File)

            for node in tree.findall('.//title'):
                node.text = str(FileNm)
            for node in tree.findall('.//northbc'):
                node.text = str(FileDesc_obj.extent.YMax)
            for node in tree.findall('.//southbc'):
                node.text = str(FileDesc_obj.extent.YMin)
            for node in tree.findall('.//westbc'):
                node.text = str(FileDesc_obj.extent.XMin)
            for node in tree.findall('.//eastbc'):
                node.text = str(FileDesc_obj.extent.XMax)        
            for node in tree.findall('.//native/nondig/formname'):
                node.text = str(os.getcwd()+"\\"+File)
            for node in tree.findall('.//native/digform/formname'):
                node.text = str(FileDesc_obj.featureType)
            for node in tree.findall('.//avlform/nondig/formname'):
                node.text = str(FileDesc_obj.extension)
            for node in tree.findall('.//avlform/digform/formname'):
                node.text = str(float(os.path.getsize(File))/int(1024))+" KB"
            for node in tree.findall('.//theme'):
                node.text = str(FileDesc_obj.spatialReference.name +" ; EPSG: "+str(FileDesc_obj.spatialReference.factoryCode))
            print node.text
            projection_info=[]
            Zone=FileDesc_obj.spatialReference.name

            if "GCS" in str(FileDesc_obj.spatialReference.name):
                projection_info=[FileDesc_obj.spatialReference.GCSName, FileDesc_obj.spatialReference.angularUnitName, FileDesc_obj.spatialReference.datumName, FileDesc_obj.spatialReference.spheroidName]
                print "Geographic Coordinate system"
            else:
                projection_info=[FileDesc_obj.spatialReference.datumName, FileDesc_obj.spatialReference.spheroidName, FileDesc_obj.spatialReference.angularUnitName, Zone[Zone.rfind(zone)-3:]]
                print "Projected Coordinate system"
            x=0
            for node in tree.findall('.//spdom'):
                for node2 in node.findall('.//keyword'):
                    print node2.text
                    node2.text = str(projection_info[x])
                    print node2.text
                    x=x+1


            tree.write(newMetaFile)

            f = open(Generated_XMLs, 'a')
            f.write(str(Count)+": "+File+"; "+newMetaFile+"; "+currentPath+"\n")
            f.close()



    #        Create_xml(currentPath)

RESULT

Solution 1

Try the following:

if any(f.startswith(existingXML) and f.endswith('.xml') for f in check_meta):
   print "exists"

The any() built-in function takes an iterable as an argument and returns true if any of the elements are true. The argument that we pass is a generator expression which will yield the value f.startswith(existingXML) and f.endswith('.xml') for each file f in your list check_meta.

A regex solution might look something like this:

regex = re.compile(re.escape(existingXML) + '.*\.xml$')
if any(regex.match(f) for f in check_meta):
    print "exists"

If you need to know which entry actually matches, use a for loop instead:

for f in check_meta:
    if f.startswith(existingXML) and f.endswith('.xml'):
        print "exists, file name:", f

Solution 2

why not just use:

searchtext = "sometext"
matching = [ f for f in os.listdir(currentPath) if f.startswith(searchtext) and ".xml" in f]

If you want to check for different extentions you can list them out.

exts = (".xml", ".tab", ".shp")
matching = [ f for f in os.listdir(currentPath) if f.startswith(searchtext) and os.path.splitext(f)[-1] in exts]

Of course you could figure out the regex to do the same thing as well.