add cli interface for archiveindexer expose as 'cdx-indexer'

add tests for cli interface
additional tests for statusheaders

pywb/utils/test/test_statusandheaders.py

@@ -1,5 +1,6 @@
 """
->>> StatusAndHeadersParser(['HTTP/1.0']).parse(BytesIO(status_headers_1))
+>>> st1 = StatusAndHeadersParser(['HTTP/1.0']).parse(BytesIO(status_headers_1))
+>>> st1
 StatusAndHeaders(protocol = 'HTTP/1.0', statusline = '200 OK', headers = [ ('Content-Type', 'ABC'),
   ('Some', 'Value'),
   ('Multi-Line', 'Value1    Also This')])
@@ -7,6 +8,18 @@ StatusAndHeaders(protocol = 'HTTP/1.0', statusline = '200 OK', headers = [ ('Con
 >>> StatusAndHeadersParser(['Other']).parse(BytesIO(status_headers_1))
 Traceback (most recent call last):
 StatusAndHeadersParserException: Expected Status Line starting with ['Other'] - Found: HTTP/1.0 200 OK
+
+# test equality op
+>>> st1 == StatusAndHeadersParser(['HTTP/1.0']).parse(BytesIO(status_headers_1))
+True
+
+# remove header
+>>> st1.remove_header('some')
+True
+
+# already removed
+>>> st1.remove_header('Some')
+False
 """
 
 

pywb/warc/archiveindexer.py

@@ -273,6 +273,7 @@ class SortedCDXWriter(CDXWriter):
         self.out.write(''.join(self.sortlist))
 
 
+#=================================================================
 class MultiFileMixin(object):
     def start_all(self):
         super(MultiFileMixin, self).start()
@@ -338,14 +339,18 @@ def index_to_file(inputs, output, sort):
 def remove_ext(filename):
     for ext in ('.arc', '.arc.gz', '.warc', '.warc.gz'):
         if filename.endswith(ext):
-            return filename[:-len(ext)]
+            filename = filename[:-len(ext)]
+            break
+
     return filename
 
+def cdx_filename(filename):
+    return remove_ext(filename) + '.cdx'
 
 def index_to_dir(inputs, output, sort):
     for fullpath, filename in iter_file_or_dir(inputs):
 
-        outpath = remove_ext(filename) + '.cdx'
+        outpath = cdx_filename(filename)
         outpath = os.path.join(output, outpath)
 
         with open(outpath, 'w') as outfile:
@@ -356,26 +361,49 @@ def index_to_dir(inputs, output, sort):
                                out=outfile).make_index()
 
 
-def main():
-    description = 'description'
-    epilog = 'epilog'
+def main(args=None):
+    description = """
+Generate .cdx index files for WARCs and ARCs
+Compressed (.warc.gz / .arc.gz) or uncompressed (.warc / .arc) formats
+are supported.
+"""
 
-    sort_help = 'sort help'
-    output_help = 'output help'
-    input_help = 'input help'
+    epilog = """
+Some examples:
+
+* Create "example.cdx" index from example.warc.gz
+{0} ./cdx/example.cdx ./warcs/example.warc.gz
+
+* Create "combined.cdx", a combined, sorted index of all warcs in ./warcs/
+{0} --sort combined.cdx ./warcs/
+
+* Create a sorted cdx per file in ./cdx/ for each archive file in ./warcs/
+{0} --sort ./cdx/ ./warcs/
+""".format(os.path.basename(sys.argv[0]))
+
+    sort_help = """
+sort the output to each file before writing to create a total ordering
+"""
+
+    output_help = """output file or directory.
+- If directory, each input file is written to a seperate output file
+  with a .cdx extension
+- If output is '-', output is written to stdout
+"""
+
+    input_help = """input file or directory
+- If directory, all archive files from that directory are read
+"""
 
     parser = ArgumentParser(description=description,
                             epilog=epilog,
                             formatter_class=RawTextHelpFormatter)
 
-    parser.add_argument('--sort', action='store_true', help=sort_help)
+    parser.add_argument('-s', '--sort', action='store_true', help=sort_help)
     parser.add_argument('output', help=output_help)
     parser.add_argument('inputs', nargs='+', help=input_help)
 
-    cmd = parser.parse_args()
-    #print cmd
-    #return
-
+    cmd = parser.parse_args(args=args)
     if cmd.output != '-' and os.path.isdir(cmd.output):
         index_to_dir(cmd.inputs, cmd.output, cmd.sort)
     else:

pywb/warc/test/test_indexing.py

@@ -1,5 +1,6 @@
 r"""
 
+#=================================================================
 # warc.gz
 >>> print_cdx_index('example.warc.gz')
  CDX N b a m s k r M S V g
@@ -37,14 +38,40 @@ metadata)/gnu.org/software/wget/warc/wget.log 20140216012908 metadata://gnu.org/
  CDX N b a m s k r M S V g
 com,example)/ 20140401000000 http://example.com/ text/html 204 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 67 134 bad.arc
 com,example)/ 20140401000000 http://example.com/ text/html 204 3I42H3S6NNFQ2MSVX7XZKYAYSCX5QBYJ - - 68 202 bad.arc
+
+# Test CLI interface -- (check for num lines)
+#=================================================================
+
+# test sort, multiple inputs
+>>> cli_lines(['--sort', '-',  TEST_WARC_DIR])
+com,example)/ 20130729195151 http://test@example.com/ warc/revisit - B2LTWWPUOYAH7UIPQ7ZUPQ4VMBSVC36A - - 591 355 example-url-agnostic-revisit.warc.gz
+org,iana,example)/ 20130702195402 http://example.iana.org/ text/html 200 B2LTWWPUOYAH7UIPQ7ZUPQ4VMBSVC36A - - 1001 353 example-url-agnostic-orig.warc.gz
+200
+
+# test writing to stdout
+>>> cli_lines(['-', TEST_WARC_DIR + 'example.warc.gz'])
+com,example)/?example=1 20140103030321 http://example.com?example=1 text/html 200 B2LTWWPUOYAH7UIPQ7ZUPQ4VMBSVC36A - - 1043 333 example.warc.gz
+org,iana)/domains/example 20140128051539 http://www.iana.org/domains/example text/html 302 JZ622UA23G5ZU6Y3XAKH4LINONUEICEG - - 577 2907 example.warc.gz
+4
+
+# test writing to temp dir
+>>> cli_lines_with_dir(TEST_WARC_DIR + 'example.warc.gz')
+example.cdx
+com,example)/?example=1 20140103030321 http://example.com?example=1 text/html 200 B2LTWWPUOYAH7UIPQ7ZUPQ4VMBSVC36A - - 1043 333 example.warc.gz
+org,iana)/domains/example 20140128051539 http://www.iana.org/domains/example text/html 302 JZ622UA23G5ZU6Y3XAKH4LINONUEICEG - - 577 2907 example.warc.gz
+4
 """
 
 from pywb import get_test_dir
-from pywb.warc.archiveindexer import ArchiveIndexer
+from pywb.warc.archiveindexer import ArchiveIndexer, main, cdx_filename
 
 from io import BytesIO
 import sys
 
+import os
+import shutil
+import tempfile
+
 TEST_CDX_DIR = get_test_dir() + 'cdx/'
 TEST_WARC_DIR = get_test_dir() + 'warcs/'
 
@@ -79,3 +106,49 @@ def test_sorted_warc_gz():
     assert_cdx_match('example.cdx', 'example.warc.gz', sort=True)
     assert_cdx_match('dupes.cdx', 'dupes.warc.gz', sort=True)
     assert_cdx_match('iana.cdx', 'iana.warc.gz', sort=True)
+
+def cli_lines(cmds):
+    buff = BytesIO()
+    orig = sys.stdout
+    sys.stdout = buff
+    main(cmds)
+    sys.stdout = orig
+    lines = buff.getvalue().rstrip().split('\n')
+
+    # print first, last, num lines
+    print (lines[1])
+    print (lines[-1])
+    print len(lines)
+
+def cli_lines_with_dir(input_):
+    try:
+        lines = None
+        tmp_dir = None
+        tmp_dir = tempfile.mkdtemp()
+
+        main([tmp_dir, input_])
+
+        filename = cdx_filename(os.path.basename(input_))
+
+        print filename
+
+        with open(os.path.join(tmp_dir, filename), 'r') as fh:
+            lines = fh.read(8192).rstrip().split('\n')
+
+    finally:
+        try:
+            if tmp_dir:
+                shutil.rmtree(tmp_dir)
+        except OSError as exc:
+            if exc.errno != 2:
+                raise
+
+    if not lines:
+        return
+
+    # print first, last, num lines
+    print (lines[1])
+    print (lines[-1])
+    print len(lines)
+
+

setup.py

@@ -72,8 +72,8 @@ setup(
         'pyyaml',
        ],
     tests_require=[
-        'WebTest',
         'pytest',
+        'WebTest',
         'pytest-cov',
         'fakeredis',
         'mock',
@@ -84,6 +84,7 @@ setup(
         [console_scripts]
         wayback = pywb.apps.wayback:main
         cdx-server = pywb.apps.cdx_server:main
+        cdx-indexer = pywb.warc.archiveindexer:main
         """,
     zip_safe=False,
     classifiers=[