MCPcopy Create free account

hub / github.com/commoncrawl/cc-index-table / functions

Functions160 in github.com/commoncrawl/cc-index-table

Methodmain
(String[] args)
src/main/java/org/commoncrawl/spark/IndexTable.java:552
Methodmain
(String[] args)
src/main/java/org/commoncrawl/spark/examples/CCIndexWarcExport.java:246
Methodmain
(String[] args)
src/main/java/org/commoncrawl/spark/examples/CCIndexExport.java:204
Functionmock_parquet_file
(path)
src/util/test/test_are_part_min_max_increasing.py:93
MethodneedsTaskCommit
(TaskAttemptContext taskContext)
src/main/java/org/commoncrawl/spark/util/NullOutputCommitter.java:35
MethodnormalizeNameAsciiCharInHostName
()
src/test/java/org/commoncrawl/net/HostNameTest.java:32
MethodnormalizeNameBlankInput
()
src/test/java/org/commoncrawl/net/HostNameTest.java:26
MethodnormalizeNameMixedPunycodeInHostname
()
src/test/java/org/commoncrawl/net/HostNameTest.java:46
MethodnormalizeNameNoAsciiInHostname
()
src/test/java/org/commoncrawl/net/HostNameTest.java:40
MethodonTaskEnd
(SparkListenerTaskEnd sparkListenerTaskEnd)
src/main/java/org/commoncrawl/spark/JobStatsListener.java:36
MethodparseOptions
(String[] args, List<String> arguments)
src/main/java/org/commoncrawl/spark/examples/CCIndexWarcExport.java:94
MethodreadSchema
()
src/test/java/org/commoncrawl/spark/TestEOTIndexTable.java:35
MethodsetHostNameAsciiHostUnchanged
()
src/test/java/org/commoncrawl/net/HostNameTest.java:74
MethodsetHostNameBrainEmojiPercentEncoded
()
src/test/java/org/commoncrawl/net/HostNameTest.java:52
MethodsetHostNameBrainEmojiUnicodeDirect
()
src/test/java/org/commoncrawl/net/HostNameTest.java:60
MethodsetHostNameLegitimateIdnUnchanged
()
src/test/java/org/commoncrawl/net/HostNameTest.java:67
MethodsetupJob
(JobContext jobContext)
src/main/java/org/commoncrawl/spark/util/NullOutputCommitter.java:27
MethodsetupTask
(TaskAttemptContext taskContext)
src/main/java/org/commoncrawl/spark/util/NullOutputCommitter.java:31
MethodtestDNSRecord
()
src/test/java/org/commoncrawl/spark/TestEOTIndexTable.java:48
MethodtestDNSrecord
()
src/test/java/org/commoncrawl/spark/TestIndexTable.java:49
MethodtestDNSrecordURI
Test DNS records, cf. <a href= "https://iipc.github.io/warc-specifications/specifications/warc-format/warc-1.1/#dns-scheme">WARC <a href="https://data
src/test/java/org/commoncrawl/net/TestURL.java:184
MethodtestFiledescUriSchemes
()
src/test/java/org/commoncrawl/net/TestURL.java:212
MethodtestFlatSchema
()
src/test/java/org/commoncrawl/spark/TestCCIndex2Table.java:30
MethodtestHostName
()
src/test/java/org/commoncrawl/net/TestURL.java:111
MethodtestHostNameDecode
()
src/test/java/org/commoncrawl/net/TestURL.java:119
MethodtestHostNameDecodeIDN
()
src/test/java/org/commoncrawl/net/TestURL.java:137
MethodtestHostNameIDN
()
src/test/java/org/commoncrawl/net/TestURL.java:128
MethodtestHostNameReversed
()
src/test/java/org/commoncrawl/net/TestURL.java:153
MethodtestHostNameTrailingDot
()
src/test/java/org/commoncrawl/net/TestURL.java:159
MethodtestIPAddress
()
src/test/java/org/commoncrawl/net/TestURL.java:89
MethodtestInvalidDomainName
()
src/test/java/org/commoncrawl/net/TestURL.java:102
MethodtestMainCrawldiagnostics
()
src/test/java/org/commoncrawl/spark/TestCCWarcFilenameParser.java:54
MethodtestMainWarcFilename
()
src/test/java/org/commoncrawl/spark/TestCCWarcFilenameParser.java:27
MethodtestMainWat
()
src/test/java/org/commoncrawl/spark/TestCCWarcFilenameParser.java:36
MethodtestMainWet
()
src/test/java/org/commoncrawl/spark/TestCCWarcFilenameParser.java:45
MethodtestMetadataRecordURI
()
src/test/java/org/commoncrawl/net/TestURL.java:204
MethodtestMinimalNestedSchema
()
src/test/java/org/commoncrawl/spark/TestIndexTable.java:44
MethodtestMinimalSchema
()
src/test/java/org/commoncrawl/spark/TestIndexTable.java:39
MethodtestNestedSchema
()
src/test/java/org/commoncrawl/spark/TestCCIndex2Table.java:38
MethodtestNewsWarcFilename
()
src/test/java/org/commoncrawl/spark/TestCCWarcFilenameParser.java:63
MethodtestNormalizeMalformedFtpShouldIgnore
()
src/test/java/org/commoncrawl/net/WarcUriTest.java:108
MethodtestNormalizeMalformedHttpUrlOK
()
src/test/java/org/commoncrawl/net/WarcUriTest.java:62
MethodtestNormalizeMalformedHttps1SlashIsFixed
()
src/test/java/org/commoncrawl/net/WarcUriTest.java:100
MethodtestNormalizeMalformedHttps3SlashesIsFixed
()
src/test/java/org/commoncrawl/net/WarcUriTest.java:84
MethodtestNormalizeMalformedHttps4SlashesIsFixed
()
src/test/java/org/commoncrawl/net/WarcUriTest.java:92
MethodtestNormalizeMalformedHttpsUrlOK
()
src/test/java/org/commoncrawl/net/WarcUriTest.java:73
MethodtestPrivateDomain
()
src/test/java/org/commoncrawl/net/TestURL.java:146
MethodtestSchema
()
src/test/java/org/commoncrawl/spark/TestEOTIndexTable.java:40
MethodtestURL
()
src/test/java/org/commoncrawl/net/TestURL.java:78
MethodtestURLinvalidURI
()
src/test/java/org/commoncrawl/net/TestURL.java:168
MethodtestWhoisRecordURI
()
src/test/java/org/commoncrawl/net/TestURL.java:192
Functiontest_ordered_files_sorted
()
src/util/test/test_are_part_min_max_increasing.py:86
Functiontest_ordered_files_unsorted
()
src/util/test/test_are_part_min_max_increasing.py:101
Functiontest_row_groups_null_stats_inorder
()
src/util/test/test_are_part_min_max_increasing.py:58
Functiontest_row_groups_null_stats_out_of_order
()
src/util/test/test_are_part_min_max_increasing.py:65
Functiontest_row_groups_overlapping
()
src/util/test/test_are_part_min_max_increasing.py:79
Functiontest_row_groups_overlapping_min_max
()
src/util/test/test_are_part_min_max_increasing.py:72
Functiontest_row_groups_sorted
()
src/util/test/test_are_part_min_max_increasing.py:31
Functiontest_row_groups_unsorted
()
src/util/test/test_are_part_min_max_increasing.py:40
Functiontest_single_row_group_sorted
()
src/util/test/test_are_part_min_max_increasing.py:25
← previous101–160 of 160, ranked by callers