X-Git-Url: https://code.communitydata.science/mediawiki_dump_tools.git/blobdiff_plain/c437b357db9ddbc552a94519d5bbcfb5180e7e3d..refs/heads/parquet_support:/wikiq diff --git a/wikiq b/wikiq index a377d19..75c1af8 100755 --- a/wikiq +++ b/wikiq @@ -250,13 +250,13 @@ class RevDataBase(): pa.field("revid", pa.int64()), pa.field("date_time", pa.timestamp('ms')), pa.field("articleid",pa.int64()), - pa.field("editorid",pa.int64()), + pa.field("editorid",pa.int64(), nullable=True), pa.field("title",pa.string()), pa.field("namespace",pa.int32()), pa.field("deleted",pa.bool_()), - pa.field("test_chars",pa.int32()), - pa.field("revert",pa.bool_()), - pa.field("reverteds",pa.list_(pa.int64())), + pa.field("text_chars",pa.int32()), + pa.field("revert",pa.bool_(), nullable=True), + pa.field("reverteds",pa.list_(pa.int64()), nullable=True), pa.field("sha1",pa.string()), pa.field("minor",pa.bool_()), pa.field("editor",pa.string()), @@ -518,7 +518,7 @@ class WikiqParser(): namespace = namespace ) - rev_data = self.matchmake(rev, rev_data) + rev_data = self.matchmake_revision(rev, rev_data) if not rev.deleted.text: # rev.text can be None if the page has no text