Take the 2-minute tour ×
Geographic Information Systems Stack Exchange is a question and answer site for cartographers, geographers and GIS professionals. It's 100% free, no registration required.

I need to create a metadata-table for all files in a File Geodatabase or Spatial Database.

It would be awesome if it were possible to automatically be updated with new filenames, and possibly even metadata (as created in the ArcGIS metadata editor).

Even partial solutions would be highly appreciated

share|improve this question

1 Answer 1

Here is a Python script for ArcGIS 10 that basically does what you want, except that the output is a CSV file, not a geodatabase table. Feel free to modify and use as you like. Note that it is not well tested and not supported, so use at your own risk.

"""
This script looks through the specified geodatabase and reports the
names of all data elements, their schema owners and their feature
dataset (if applicable). Certain metadata elements such as abstract,
purpose and search keys are also reported.

The output is a CSV file that can be read by Excel, ArcGIS, etc.

Only geodatabases are supported, not folder workspaces.

Note: If run from outside of ArcToolbox, you will need to add
the metadata tool assemblies to the Global Assembly Cache.
See: http://forums.arcgis.com/threads/74468-Python-Errors-in-IDLE-when-processing-metadata

Parameters:
    0 - Input workspace (file geodatabase, personal geodatabase,
            or SDE connection file)
    1 - Output CSV file

Date updated: 2/11/2013
"""

import arcpy
import os
import csv
import tempfile
import codecs
import cStringIO
from xml.etree.ElementTree import ElementTree

def ListWorkspaceContentsAndMetadata(workspace):
    """Generator function that lists the contents of the geodatabase including those within feature datasets.
       Certain metadata elements are also listed. Only geodatabases are supported, not folder workspaces."""

    if not arcpy.Exists(workspace):
        raise ValueError("Workspace %s does not exist!" % workspace)

    desc = arcpy.Describe(workspace)

    if not desc.dataType in ['Workspace', 'FeatureDataset']:
        if not hasattr(desc, "workspaceType") or not desc.workspaceType in ["LocalDatabase", "RemoteDatabase"]:
            raise ValueError("Workspace %s is not a geodatabase!" % workspace)

    children = desc.children
    if desc.dataType == 'FeatureDataset':
        validationWorkspace = os.path.dirname(workspace)
        fdsName = arcpy.ParseTableName(desc.name, validationWorkspace).split(",")[2].strip() # Get the short name of the feature dataset (sans database/owner name)
    else:
        validationWorkspace = workspace
        fdsName = ""

    for child in children:
        # Parse the full table name into database, owner, table name
        database, owner, tableName = [i.strip() if i.strip() != "(null)" else "" for i in arcpy.ParseTableName(child.name, validationWorkspace).split(",")]
        datasetType = child.datasetType if hasattr(child, "datasetType") else ""
        alias = child.aliasName if hasattr(child, "aliasName") else ""
        outrow = [owner, tableName, alias, fdsName, datasetType]
        try:
            outrow.extend(GetMetadataItems(child.catalogPath))
        except:
            pass
        print ",".join(outrow)
        yield outrow

        # Recurse to get the contents of feature datasets
        if datasetType == 'FeatureDataset':
            for outrow in ListWorkspaceContentsAndMetadata(child.catalogPath):
                yield outrow

def WriteCSVFile(csvfile, rows, header=None):
    """Creates a CSV file from the input header and row sequences"""
    with open(csvfile, 'wb') as f:
        f.write(codecs.BOM_UTF8) # Write Byte Order Mark character so Excel knows this is a UTF-8 file
        w = UnicodeWriter(f, dialect='excel', encoding='utf-8')
        if header:
            w.writerow(header)
        w.writerows(rows)

def CreateHeaderRow():
    """Specifies the column names (header row) for the CSV file"""
    return ("OWNER", "TABLE_NAME", "ALIAS", "FEATURE_DATASET", "DATASET_TYPE", "ORIGINATOR", "CONTACT_ORG", "ABSTRACT", "PURPOSE", "SEARCH_KEYS", "THEME_KEYS")

def CreateDummyXMLFile():
    """Creates an XML file with the required root element 'metadata' in
    the user's temporary files directory. Returns the path to the file.
    The calling code is responsible for deleting the temporary file."""
    tempdir = tempfile.gettempdir()
    fd, filepath = tempfile.mkstemp(".xml", text=True)
    with os.fdopen(fd, "w") as f:
        f.write("<metadata />")
        f.close()
    return filepath

def GetMetadataElementTree(dataset):
    """Creates and returns an ElementTree object from the specified
    dataset's metadata"""
    xmlfile = CreateDummyXMLFile()
    arcpy.MetadataImporter_conversion(dataset, xmlfile)
    tree = ElementTree()
    tree.parse(xmlfile)
    os.remove(xmlfile)
    return tree

def GetElementText(tree, elementPath):
    """Returns the specified element's text if it exists or an empty
    string if not."""
    element = tree.find(elementPath)
    return element.text if element != None else ""

def GetFirstElementText(tree, elementPaths):
    """Returns the first found element matching one of the specified
    element paths"""
    result = ""
    for elementPath in elementPaths:
        element = tree.find(elementPath)
        if element != None:
            result = element.text
            break
    return result

def ListElementsText(tree, elementPath):
    """Returns a comma+space-separated list of the text values of all
    instances of the specified element, or an empty string if none are
    found."""
    elements = tree.findall(elementPath)
    if elements:
        return ", ".join([element.text for element in elements])
    else:
        return ""

def GetMetadataItems(dataset):
    """Retrieves certain metadata text elements from the specified dataset"""
    tree = GetMetadataElementTree(dataset)
    originator = GetElementText(tree, "idinfo/citation/citeinfo/origin") # Originator
    pocorg = GetFirstElementText(tree, ("idinfo/ptcontac/cntinfo/cntperp/cntorg", # Point of contact organization (person primary contact)
                                        "idinfo/ptcontac/cntinfo/cntorgp/cntorg")) # Point of contact organization (organization primary contact)
    abstract = GetElementText(tree, "idinfo/descript/abstract") # Abstract
    purpose = GetElementText(tree, "idinfo/descript/purpose") # Purpose
    searchkeys = ListElementsText(tree, "dataIdInfo/searchKeys/keyword") # Search keywords
    themekeys = ListElementsText(tree, "idinfo/keywords/theme/themekey") # Theme keywords
    del tree
    metadataItems = (originator, pocorg, abstract, purpose, searchkeys, themekeys)
    return metadataItems

class UnicodeWriter:
    """
    A CSV writer which will write rows to CSV file "f",
    which is encoded in the given encoding.
    """

    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
        # Redirect output to a queue
        self.queue = cStringIO.StringIO()
        self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
        self.stream = f
        self.encoder = codecs.getincrementalencoder(encoding)()

    def writerow(self, row):
        self.writer.writerow([s.encode("utf-8") for s in row])
        # Fetch UTF-8 output from the queue ...
        data = self.queue.getvalue()
        data = data.decode("utf-8")
        # ... and reencode it into the target encoding
        data = self.encoder.encode(data)
        # write to the target stream
        self.stream.write(data)
        # empty queue
        self.queue.truncate(0)

    def writerows(self, rows):
        for row in rows:
            self.writerow(row)

if __name__ == '__main__':
    workspace = arcpy.GetParameterAsText(0)
    csvFile = arcpy.GetParameterAsText(1)
    headerRow = CreateHeaderRow()
    print headerRow
    datasetRows = ListWorkspaceContentsAndMetadata(workspace)
    WriteCSVFile(csvFile, datasetRows, headerRow)
share|improve this answer
1  
Great resource! –  artwork21 Feb 11 '13 at 20:05
    
Thanks, there are some bugs with this still I think though :) –  blah238 Feb 11 '13 at 20:56
1  
Alright hopefully the bugs are squashed now :) –  blah238 Feb 11 '13 at 22:17
1  
Excellent piece of code. Thank you for sharing it! –  Víctor Velarde Aug 25 at 11:06

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.