This is an automated email from the ASF dual-hosted git repository.
kgyrtkirk pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hive.git
The following commit(s) were added to refs/heads/master by this push:
new 0099b14aa6a HIVE-25733: Add check-spelling/check-spelling (#2809)
(Josh Soref reviewed by Zoltan Haindrich)
0099b14aa6a is described below
commit 0099b14aa6a50d4470b057e93a95a7391b74add7
Author: Josh Soref <2119212+jso...@users.noreply.github.com>
AuthorDate: Mon Jun 13 11:05:41 2022 -0400
HIVE-25733: Add check-spelling/check-spelling (#2809) (Josh Soref reviewed
by Zoltan Haindrich)
---
.github/actions/spelling/README.md | 17 ++
.github/actions/spelling/advice.md | 25 ++
.github/actions/spelling/allow.txt | 0
.github/actions/spelling/excludes.txt | 57 +++++
.github/actions/spelling/expect.txt | 449 ++++++++++++++++++++++++++++++++++
.github/actions/spelling/only.txt | 1 +
.github/actions/spelling/patterns.txt | 38 +++
.github/actions/spelling/reject.txt | 7 +
.github/workflows/spelling.yml | 69 ++++++
9 files changed, 663 insertions(+)
diff --git a/.github/actions/spelling/README.md
b/.github/actions/spelling/README.md
new file mode 100644
index 00000000000..749294b33fb
--- /dev/null
+++ b/.github/actions/spelling/README.md
@@ -0,0 +1,17 @@
+# check-spelling/check-spelling configuration
+
+File | Purpose | Format | Info
+-|-|-|-
+<!--
+[dictionary.txt](dictionary.txt) | Replacement dictionary (creating this file
will override the default dictionary) | one word per line |
[dictionary](https://github.com/check-spelling/check-spelling/wiki/Configuration#dictionary)
+-->
+[allow.txt](allow.txt) | Add words to the dictionary | one word per line (only
letters and `'`s allowed) |
[allow](https://github.com/check-spelling/check-spelling/wiki/Configuration#allow)
+[reject.txt](reject.txt) | Remove words from the dictionary (after allow) |
grep pattern matching whole dictionary words |
[reject](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-reject)
+[excludes.txt](excludes.txt) | Files to ignore entirely | perl regular
expression |
[excludes](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-excludes)
+[only.txt](only.txt) | Only check matching files (applied after excludes) |
perl regular expression |
[only](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-only)
+[patterns.txt](patterns.txt) | Patterns to ignore from checked lines | perl
regular expression (order matters, first match wins) |
[patterns](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-patterns)
+[expect.txt](expect.txt) | Expected words that aren't in the dictionary | one
word per line (sorted, alphabetically) |
[expect](https://github.com/check-spelling/check-spelling/wiki/Configuration#expect)
+[advice.md](advice.md) | Supplement for GitHub comment when unrecognized words
are found | GitHub Markdown |
[advice](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-advice)
+
+Note: you can replace any of these files with a directory by the same name
(minus the suffix)
+and then include multiple files inside that directory (with that suffix) to
merge multiple files together.
diff --git a/.github/actions/spelling/advice.md
b/.github/actions/spelling/advice.md
new file mode 100644
index 00000000000..c83423a8ef6
--- /dev/null
+++ b/.github/actions/spelling/advice.md
@@ -0,0 +1,25 @@
+<!-- See
https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples%3A-advice
--> <!-- markdownlint-disable MD033 MD041 -->
+<details><summary>If the flagged items do not appear to be text</summary>
+
+If items relate to a ...
+* well-formed pattern.
+
+ If you can write a
[pattern](https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples:-patterns)
that would match it,
+ try adding it to the `patterns.txt` file.
+
+ Patterns are Perl 5 Regular Expressions - you can [test](
+https://www.regexplanet.com/advanced/perl/) yours before committing to verify
it will match your lines.
+
+ Note that patterns can't match multiline strings.
+
+* binary file.
+
+ Please add a file path to the `excludes.txt` file matching the containing
file.
+
+ File paths are Perl 5 Regular Expressions - you can [test](
+https://www.regexplanet.com/advanced/perl/) yours before committing to verify
it will match your files.
+
+ `^` refers to the file's path from the root of the repository, so
`^README\.md$` would exclude [README.md](
+../tree/HEAD/README.md) (on whichever branch you're using).
+
+</details>
diff --git a/.github/actions/spelling/allow.txt
b/.github/actions/spelling/allow.txt
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/.github/actions/spelling/excludes.txt
b/.github/actions/spelling/excludes.txt
new file mode 100644
index 00000000000..f15a0e0c9ca
--- /dev/null
+++ b/.github/actions/spelling/excludes.txt
@@ -0,0 +1,57 @@
+# See
https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples:-excludes
+(?:^|/)(?i)COPYRIGHT
+(?:^|/)(?i)LICEN[CS]E
+(?:^|/)package(?:-lock|)\.json$
+(?:^|/)vendor/
+ignore$
+LICENSE
+\.avi$
+\.avro$
+\.bz2$
+\.deflate$
+\.eot$
+\.gif$
+\.gz$
+\.ico$
+\.jar$
+\.jceks$
+\.jks$
+\.jpe?g$
+\.jpeg$
+\.jpg$
+\.keep$
+\.lock$
+\.log$
+\.map$
+\.min\.
+\.min\..
+\.mod$
+\.mp[34]$
+\.orc$
+\.out$
+\.out\.
+\.parq$
+\.parquet$
+\.png$
+\.q$
+\.rc$
+\.rcfile$
+\.seq$
+\.svg$
+\.ttf$
+\.wav$
+\.woff$
+^data/files
+^data/scripts/q_test_cleanup\.sql$
+^docs/people\.md$
+^errata\.txt$
+^hplsql/src/test/queries/local/to_timestamp\.sql$
+^iceberg-handler/checkstyle/checkstyle-suppressions\.xml$
+^itests/hive-unit/src/test/resources/simple-saml-idp-metadata-template\.xml$
+^llap-common/src/gen/protobuf/gen-java/org/apache/hadoop/hive/llap/daemon/rpc/LlapDaemonProtocolProtos\.java$
+^llap-common/src/gen/protobuf/gen-java/org/apache/hadoop/hive/llap/plugin/rpc/LlapPluginProtocolProtos\.java$
+^serde/src/test/resources/json/single_pixel\.json$
+^spark-client/src/test/java/org/apache/hive/spark/client/TestSparkClient\.java$
+^testutils/ptest2/src/test/resources/
+^\.github/
+^\Qql/src/test/resources/hsmm/hsmm_cfg_01.yaml\E$
diff --git a/.github/actions/spelling/expect.txt
b/.github/actions/spelling/expect.txt
new file mode 100644
index 00000000000..39b9d7fc583
--- /dev/null
+++ b/.github/actions/spelling/expect.txt
@@ -0,0 +1,449 @@
+AAAAABJRU
+aarry
+abcd
+abcde
+abcdef
+abcdefg
+abcdefgh
+abcdefghij
+abcdefghijklmnopqrstuvwxyz
+abyte
+adouble
+aeden
+afields
+AFq
+agrw
+aloi
+alphadigits
+amap
+ANANCIENTBLUEBOX
+ANull
+anullint
+anullstring
+aoig
+arecord
+args
+arraycopy
+asd
+ASF
+ashort
+astring
+ati
+attr
+aunion
+Autogenerated
+avro
+avrotest
+avsc
+bais
+baoi
+baos
+BArray
+basedir
+bdoi
+bdw
+bigint
+binarysortable
+bitfield
+bitset
+blahblahblah
+bnoi
+boi
+BTEQ
+buf
+byoi
+bytearrayinput
+bytebuffer
+bytecode
+byteinfo
+BYTEINT
+byw
+cae
+cfields
+charset
+classname
+clazz
+Cloneable
+cmp
+CODEPOINT
+coi
+columnset
+complexpb
+concat
+concating
+config
+cpp
+Cpy
+CReadable
+crlf
+csv
+ctl
+ctor
+ctype
+cwiki
+CYBERMEN
+DALEKS
+daos
+datetime
+ddl
+decs
+Deque
+deser
+deserialization
+deserialize
+deserialized
+deserializer
+deserializing
+dest
+dfr
+dfs
+dfw
+Dio
+doi
+DOTALL
+DOUBLEVALUE
+dti
+dtoi
+dtype
+DZone
+ecapseman
+ecast
+Eccleston
+eid
+ele
+elif
+endian
+endif
+entryinput
+entryoutput
+enum
+enumlist
+enumness
+enumset
+eoi
+EQVR
+Escapables
+ESCAPECHAR
+ETX
+etype
+facebook
+fastload
+ffec
+fff
+fieldids
+Fieldname
+firstfield
+foi
+foreach
+fourbytes
+frac
+ftype
+gallifrey
+garw
+gdr
+gdw
+gmt
+hackersdelight
+hadoop
+hamcrest
+hashcode
+Hashtable
+hbase
+hcoi
+hconf
+hcw
+HDFS
+hdoi
+hdw
+HIVEFETCHOUTPUTSERDE
+hiw
+href
+http
+hvc
+hvoi
+iae
+IBegin
+identd
+idx
+ifndef
+ILength
+impl
+inited
+inlining
+inp
+INPATH
+inputformat
+inputmpkeyoi
+inputmpoi
+inputmpvalueoi
+inputstream
+instanceof
+interop
+Ints
+INTVALUE
+ioe
+ioi
+iosfwd
+iprot
+IScheme
+isdigit
+isinstance
+islist
+isset
+itest
+ith
+JAGRAFESS
+javabean
+Javadoc
+javax
+jdbc
+jdm
+Jggg
+Joda
+json
+junit
+kitchsink
+ktype
+kyro
+lasti
+lazybinary
+lazydio
+lazympkeyoi
+lazympoi
+lazympvalueoi
+lazyobj
+LAZYSIMPLE
+LBRACE
+LBRACKET
+len
+LINTSTRING
+loi
+LONGVALUE
+lstring
+ltype
+mapkey
+mapsize
+MAXVALUE
+mctesty
+Mega
+megastruct
+memoizes
+memoizing
+metadata
+metastore
+millis
+MINVALUE
+mkdirs
+mkoi
+mstring
+MSTRINGSTRING
+mti
+mtype
+mvoi
+mydouble
+myint
+mylong
+mysql
+MYSTRING
+namespace
+nano
+narray
+NByte
+Nestedin
+nfe
+nio
+noexcept
+nokey
+nondigits
+nullability
+nullableenum
+nullableint
+nullptr
+nullsafe
+nullstring
+NUu
+objectinspector
+objs
+ois
+olist
+omap
+opencsv
+oprot
+ostream
+outputmp
+outputstream
+params
+php
+plugin
+png
+println
+prj
+prot
+protobuf
+protoc
+pti
+ptr
+ptype
+QLFTWHXe
+QUOTECHAR
+RAWSTRING
+rawtypes
+RBRACE
+RBRACKET
+rdata
+readcolumn
+recv
+reencode
+reencoding
+regex
+RESULTSET
+returncode
+rhs
+rmi
+rossa
+RRID
+sde
+SEPARATORCHAR
+sequencefile
+serde
+serdeing
+SERDEPROPERTIES
+serializer
+shiftbits
+SInt
+SINTSTRING
+SJAAAADUl
+slist
+SLITHEEN
+smallint
+soi
+spoi
+sql
+src
+ssoi
+stackoverflow
+sti
+stringify
+stringlist
+stringset
+STRINGVALUE
+strtod
+structlist
+structs
+structset
+STX
+stype
+subrecord
+superfield
+sys
+TApplication
+TBase
+TBinary
+tbl
+tblproperties
+TBool
+TByte
+TColumn
+TCompact
+TConfiguration
+TConstant
+TCTL
+TDouble
+TEnum
+teradata
+testcompare
+testfield
+testget
+testi
+testthrift
+TException
+TEXTFILE
+TField
+TFrozen
+threebytes
+Throwable
+timelabel
+timestamplocal
+TIMESTAMPLOCALTZ
+timestamptz
+timezone
+TInput
+tinyint
+TIO
+tlist
+tmap
+TMemory
+TMessage
+tmp
+todo
+tokenized
+tokenizer
+tokenizing
+TOutput
+tprotocol
+TRecursive
+TReflection
+TRegex
+tsd
+TSet
+tsoi
+TSOP
+TSPEC
+TString
+tstruct
+tstz
+tsw
+TTo
+ttransport
+TTuple
+ttype
+TUnion
+typedef
+typeinfo
+typestring
+udf
+uint
+ULong
+uncompressing
+unescape
+unicode
+Uniob
+UNIONFIELD
+UNIONMSTRINGSTRING
+uniontype
+uoi
+uri
+urie
+url
+usoi
+utf
+Utils
+utype
+uuid
+vals
+varbyte
+varchar
+varname
+vchar
+versioned
+vidt
+vints
+viter
+viyt
+vlong
+voi
+vtype
+wiki
+workaround
+writables
+www
+XDh
+xfer
+xml
+xmlns
+xsi
+yadda
+yes'okay
+yyyy
+YYYYMMDD
+zid
diff --git a/.github/actions/spelling/only.txt
b/.github/actions/spelling/only.txt
new file mode 100644
index 00000000000..a1dd009c742
--- /dev/null
+++ b/.github/actions/spelling/only.txt
@@ -0,0 +1 @@
+^serde/
diff --git a/.github/actions/spelling/patterns.txt
b/.github/actions/spelling/patterns.txt
new file mode 100644
index 00000000000..0600af057b7
--- /dev/null
+++ b/.github/actions/spelling/patterns.txt
@@ -0,0 +1,38 @@
+# See
https://github.com/check-spelling/check-spelling/wiki/Configuration-Examples:-patterns
+
+# stackexchange -- https://stackexchange.com/feeds/sites
+\b(?:askubuntu|serverfault|stack(?:exchange|overflow)|superuser).com/questions/\d+/[a-z-]+
+# w3
+\bw3\.org/[-0-9a-zA-Z/#.]+
+# mvnrepository.com
+\bmvnrepository\.com/[-0-9a-z./]+
+# URL escaped characters
+\%[0-9A-F]{2}
+# sha-1
+"[0-9a-f]{40}"
+# hex digits including css/html color classes:
+(?:[\\0][xX]|\\u|[uU]\+|#|\%23)[0-9a-fA-FgGrR]{2,}[uU]?[lL]{0,2}\b
+# uuid:
+[{"'][0-9a-fA-F]{8}-(?:[0-9a-fA-F]{4}-){3}[0-9a-fA-F]{12}['"}]
+# curl arguments
+\b(?:)curl(?:\s+-[a-zA-Z]+)+
+# tar arguments
+\b(?:)tar(?:\s+-[a-zA-Z]+|\s[a-z]+)+
+# decode
+\.decode\("[0-9a-zA-Z]+"
+#
+"[0-9a-f]{80,}"
+# pom.xml
+<(additionalClasspathElement|arg|(?:artifact|group)Id|id|installDir|jvmArgs|mainClass|shadedClassifierName|template(?:Base|Source|Output)Dir|version)>[^<]*</\1>
+\b(?:(?:build|template(?:Base|Source|Output))Dir|(?:to|)dir|location)="[^"]*"
+xsi:schemaLocation="[^"]*"
+# java
+\bimport (?:com|org)\.[a-z0-9.]*\b
+#
ql/src/gen/protobuf/gen-java/org/apache/hadoop/hive/ql/hooks/proto/HiveHookEvents.java
+016Hiv"
+# serde/src/java/org/apache/hadoop/hive/serde2/avro/SchemaToTypeInfo.java
+\bNULLable\b
+#
serde/src/test/org/apache/hadoop/hive/serde2/lazy/fast/TestLazySimpleDeserializeRead.java
+"This\\{1,2}n..*"
+# ignore long runs of a single character:
+\b([A-Za-z])\g{-1}{3,}\b
diff --git a/.github/actions/spelling/reject.txt
b/.github/actions/spelling/reject.txt
new file mode 100644
index 00000000000..a5ba6f6390e
--- /dev/null
+++ b/.github/actions/spelling/reject.txt
@@ -0,0 +1,7 @@
+^attache$
+benefitting
+occurence
+Sorce
+^[Ss]pae
+^untill
+^wether
diff --git a/.github/workflows/spelling.yml b/.github/workflows/spelling.yml
new file mode 100644
index 00000000000..16f6f75333e
--- /dev/null
+++ b/.github/workflows/spelling.yml
@@ -0,0 +1,69 @@
+name: Spell checking
+on:
+ push:
+ branches: ["**"]
+ tags-ignore: ["**"]
+ pull_request_target:
+
+jobs:
+ spelling:
+ name: Spell checking
+ permissions:
+ contents: read
+ pull-requests: read
+ outputs:
+ internal_state_directory: ${{
steps.spelling.outputs.internal_state_directory }}
+ runs-on: ubuntu-latest
+ if: "contains(github.event_name, 'pull_request') || github.event_name ==
'push'"
+ concurrency:
+ group: spelling-${{ github.event.pull_request.number || github.ref }}
+ # note: If you use only_check_changed_files, you do not want
cancel-in-progress
+ cancel-in-progress: true
+ steps:
+ - name: checkout-merge
+ if: "contains(github.event_name, 'pull_request')"
+ uses: actions/checkout@v2
+ with:
+ ref: refs/pull/${{github.event.pull_request.number}}/merge
+ - name: checkout
+ if: github.event_name == 'push'
+ uses: actions/checkout@v2
+ - name: check-spelling
+ id: spelling
+ uses: check-spelling/check-spelling@v0.0.20-alpha3
+ with:
+ suppress_push_for_open_pull_request: 1
+ post_comment: 0
+ - name: store-comment
+ if: failure()
+ uses: actions/upload-artifact@v2
+ with:
+ retention-days: 1
+ name: "check-spelling-comment-${{ github.run_id }}"
+ path: |
+ ${{ steps.spelling.outputs.internal_state_directory }}
+
+ comment:
+ name: Comment
+ runs-on: ubuntu-latest
+ needs: spelling
+ permissions:
+ contents: write
+ pull-requests: write
+ if: always() && needs.spelling.result == 'failure' &&
needs.spelling.outputs.internal_state_directory
+ steps:
+ - name: checkout
+ uses: actions/checkout@v2
+ - name: set up
+ run: |
+ mkdir /tmp/data
+ - name: retrieve-comment
+ uses: actions/download-artifact@v2
+ with:
+ name: "check-spelling-comment-${{ github.run_id }}"
+ path: /tmp/data
+ - name: comment
+ uses: check-spelling/check-spelling@v0.0.20-alpha3
+ with:
+ custom_task: comment
+ internal_state_directory: /tmp/data
