collective/mediawiki_dump_tools
16
0
Fork 0
Code Issues Pull Requests Activity

change order of fields.

Browse Source
This commit is contained in:
Nathan TeBlunthuis 2025-05-29 18:10:59 -07:00
parent f39ceefa4a
commit a9f76a0f62
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
wikiq
View File

@ -266,14 +266,14 @@ class RevDataBase:
pa.field("title",pa.string()), pa.field("title",pa.string()),
pa.field("namespace",pa.int32()), pa.field("namespace",pa.int32()),
pa.field("deleted",pa.bool_()), pa.field("deleted",pa.bool_()),
pa.field("edit_summary",pa.string()),
pa.field("text_chars",pa.int32()), pa.field("text_chars",pa.int32()),
pa.field("revert",pa.bool_(), nullable=True), pa.field("revert",pa.bool_(), nullable=True),
pa.field("reverteds",pa.list_(pa.int64()), nullable=True), pa.field("reverteds",pa.list_(pa.int64()), nullable=True),
pa.field("sha1",pa.string()), pa.field("sha1",pa.string()),
pa.field("minor",pa.bool_()), pa.field("minor",pa.bool_()),
pa.field("editor",pa.string()), pa.field("editor",pa.string()),
pa.field("anon",pa.bool_()), pa.field("anon",pa.bool_())
pa.field("edit_summary",pa.string())
] ]
# pyarrow is a columnar format, so most of the work happens in the flush_parquet_buffer function # pyarrow is a columnar format, so most of the work happens in the flush_parquet_buffer function