Use pqarrow in zio/parquetio

docs/commands/zq.md

@@ -302,7 +302,7 @@ echo '{x:1}{s:"hello"}' | zq -o out.parquet -f parquet -
 ```
 causes this error
 ```mdtest-output
-Parquet output requires uniform records but multiple types encountered (consider 'fuse')
+parquetio: encountered multiple types (consider 'fuse'): {x:int64} and {s:string}
 ```
 
 #### 3.4.1 Fusing Schemas

go.mod

@@ -9,7 +9,6 @@ require (
 	github.com/araddon/dateparse v0.0.0-20210429162001-6b43995a97de
 	github.com/aws/aws-sdk-go v1.36.17
 	github.com/axiomhq/hyperloglog v0.0.0-20191112132149-a4c4c47bc57f
-	github.com/fraugster/parquet-go v0.10.1-0.20220222153523-e6b70a8a7212
 	github.com/go-redis/redis/v8 v8.4.11
 	github.com/golang-jwt/jwt/v4 v4.4.3
 	github.com/golang/mock v1.5.0

go.sum

@@ -55,7 +55,6 @@ github.com/araddon/dateparse v0.0.0-20210429162001-6b43995a97de h1:FxWPpzIjnTlhP
 github.com/araddon/dateparse v0.0.0-20210429162001-6b43995a97de/go.mod h1:DCaWoUhZrYW9p1lxo/cm8EmUOOzAPSEZNGF2DK1dJgw=
 github.com/arbovm/levenshtein v0.0.0-20160628152529-48b4e1c0c4d0 h1:jfIu9sQUG6Ig+0+Ap1h4unLjW6YQJpKZVmUzxsD4E/Q=
 github.com/arbovm/levenshtein v0.0.0-20160628152529-48b4e1c0c4d0/go.mod h1:t2tdKJDJF9BV14lnkjHmOQgcvEKgtqs5a1N3LNdJhGE=
-github.com/armon/consul-api v0.0.0-20180202201655-eb2c6b5be1b6/go.mod h1:grANhF5doyWs3UAsr3K4I6qtAmlQcZDesFNEHPZAzj8=
 github.com/aws/aws-sdk-go v1.36.17 h1:8zTvseyGhgs3uQAzkgnFy7dvTo+ZnZLYmrhnopFxYME=
 github.com/aws/aws-sdk-go v1.36.17/go.mod h1:hcU610XS61/+aQV88ixoOzUoG7v3b31pl2zKMmprdro=
 github.com/axiomhq/hyperloglog v0.0.0-20191112132149-a4c4c47bc57f h1:y06x6vGnFYfXUoVMbrcP1Uzpj4JG01eB5vRps9G8agM=
@@ -75,10 +74,6 @@ github.com/chzyer/readline v0.0.0-20180603132655-2972be24d48e/go.mod h1:nSuG5e5P
 github.com/chzyer/test v0.0.0-20180213035817-a1ea475d72b1/go.mod h1:Q3SI9o4m/ZMnBNeIyt5eFwwo7qiLfzFZmjNmxjkiQlU=
 github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
 github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc=
-github.com/coreos/etcd v3.3.10+incompatible/go.mod h1:uF7uidLiAD3TWHmW31ZFd/JWoc32PjwdhPthX9715RE=
-github.com/coreos/go-etcd v2.0.0+incompatible/go.mod h1:Jez6KQU2B/sWsbdaef3ED8NzMklzPG4d5KIOhIy30Tk=
-github.com/coreos/go-semver v0.2.0/go.mod h1:nnelYz7RCh+5ahJtPPxZlU+153eP4D4r3EedlOD2RNk=
-github.com/cpuguy83/go-md2man v1.0.10/go.mod h1:SmD6nW6nTyfqj6ABTjUi3V3JVMnlJmwcJI5acqYI6dE=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
@@ -93,8 +88,6 @@ github.com/envoyproxy/go-control-plane v0.9.0/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymF
 github.com/envoyproxy/go-control-plane v0.9.1-0.20191026205805-5f8ba28d4473/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
 github.com/envoyproxy/go-control-plane v0.9.4/go.mod h1:6rpuAdCZL397s3pYoYcLgu1mIlRU8Am5FuJP05cCM98=
 github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c=
-github.com/fraugster/parquet-go v0.10.1-0.20220222153523-e6b70a8a7212 h1:u7X3aZRlWSm18x0EysX9szRULhH7QYQv7UkxW1yHbik=
-github.com/fraugster/parquet-go v0.10.1-0.20220222153523-e6b70a8a7212/go.mod h1:dGzUxdNqXsAijatByVgbAWVPlFirnhknQbdazcUIjY0=
 github.com/fsnotify/fsnotify v1.4.7/go.mod h1:jwhsz4b93w/PPRr/qN1Yymfu8t87LnFCMoQvtojpjFo=
 github.com/fsnotify/fsnotify v1.4.9 h1:hsms1Qyu0jgnwNXIxa+/V/PDsU6CfLf6CNO8H7IWoS4=
 github.com/fsnotify/fsnotify v1.4.9/go.mod h1:znqG4EE+3YCdAaPaxE2ZRY/06pZUdp0tY4IgpuI1SZQ=
@@ -189,10 +182,8 @@ github.com/hashicorp/golang-lru v0.5.0/go.mod h1:/m3WP610KZHVQ1SGc6re/UDhFvYD7pJ
 github.com/hashicorp/golang-lru v0.5.1/go.mod h1:/m3WP610KZHVQ1SGc6re/UDhFvYD7pJ4Ao+sR/qLZy8=
 github.com/hashicorp/golang-lru/v2 v2.0.1 h1:5pv5N1lT1fjLg2VQ5KWc7kmucp2x/kvFOnxuVTqZ6x4=
 github.com/hashicorp/golang-lru/v2 v2.0.1/go.mod h1:QeFd9opnmA6QUJc5vARoKUSoFhyfM2/ZepoAG6RGpeM=
-github.com/hashicorp/hcl v1.0.0/go.mod h1:E5yfLk+7swimpb2L/Alb/PJmXilQ/rhwaUYs4T20WEQ=
 github.com/hpcloud/tail v1.0.0/go.mod h1:ab1qPbhIpdTxEkNHXyeSf5vhxWSCs/tWer42PpOxQnU=
 github.com/ianlancetaylor/demangle v0.0.0-20181102032728-5e5cf60278f6/go.mod h1:aSSvb/t6k1mPoxDqO4vJh6VOCGPwU4O0C2/Eqndh1Sc=
-github.com/inconshreveable/mousetrap v1.0.0/go.mod h1:PxqpIevigyE2G7u3NXJIT2ANytuPF1OarO4DADm73n8=
 github.com/influxdata/influxdb v1.7.6/go.mod h1:qZna6X/4elxqT3yI9iZYdZrWWdeFOOprn86kgg4+IzY=
 github.com/jmespath/go-jmespath v0.4.0 h1:BEgLn5cpjn8UN1mAw4NjwDrS35OdebyEtFe+9YPoQUg=
 github.com/jmespath/go-jmespath v0.4.0/go.mod h1:T8mJZnbsbmF+m6zOOFylbeCJqk5+pHWvzYPziyZiYoo=
@@ -225,7 +216,6 @@ github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/leodido/go-urn v1.1.0/go.mod h1:+cyI34gQWZcE1eQU7NVgKkkzdXDQHr1dBMtdAPozLkw=
-github.com/magiconair/properties v1.8.0/go.mod h1:PppfXfuXeibc/6YijjN8zIbojt8czPbwD3XqdrwzmxQ=
 github.com/mattn/go-isatty v0.0.9/go.mod h1:YNRxwqDuOph6SZLI9vUUz6OYw3QyUt7WiY2yME+cCiQ=
 github.com/mattn/go-isatty v0.0.17 h1:BTarxUcIeDqL27Mc+vyvdWYSL28zpIhv3RoTdsLMPng=
 github.com/mattn/go-isatty v0.0.17/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
@@ -238,8 +228,6 @@ github.com/minio/asm2plan9s v0.0.0-20200509001527-cdd76441f9d8 h1:AMFGa4R4MiIpsp
 github.com/minio/asm2plan9s v0.0.0-20200509001527-cdd76441f9d8/go.mod h1:mC1jAcsrzbxHt8iiaC+zU4b1ylILSosueou12R++wfY=
 github.com/minio/c2goasm v0.0.0-20190812172519-36a3d3bbc4f3 h1:+n/aFZefKZp7spd8DFdX7uMikMLXX4oubIzJF4kv/wI=
 github.com/minio/c2goasm v0.0.0-20190812172519-36a3d3bbc4f3/go.mod h1:RagcQ7I8IeTMnF8JTXieKnO4Z6JCsikNEzj0DwauVzE=
-github.com/mitchellh/go-homedir v1.1.0/go.mod h1:SfyaCUpYCn1Vlf4IUYiD9fPX4A5wJrkLzIz1N1q0pr0=
-github.com/mitchellh/mapstructure v1.1.2/go.mod h1:FVVH3fgwuzCH5S8UJGiWEs2h04kUh9fWfEaFds41c1Y=
 github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
 github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
 github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
@@ -261,7 +249,6 @@ github.com/paulbellamy/ratecounter v0.2.0 h1:2L/RhJq+HA8gBQImDXtLPrDXK5qAj6ozWVK
 github.com/paulbellamy/ratecounter v0.2.0/go.mod h1:Hfx1hDpSGoqxkVVpBi/IlYD7kChlfo5C6hzIHwPqfFE=
 github.com/pbnjay/memory v0.0.0-20190104145345-974d429e7ae4 h1:MfIUBZ1bz7TgvQLVa/yPJZOGeKEgs6eTKUjz3zB4B+U=
 github.com/pbnjay/memory v0.0.0-20190104145345-974d429e7ae4/go.mod h1:RMU2gJXhratVxBDTFeOdNhd540tG57lt9FIUV0YLvIQ=
-github.com/pelletier/go-toml v1.2.0/go.mod h1:5z9KED0ma1S8pY6P1sdut58dfprrGBbd/94hg7ilaic=
 github.com/peterh/liner v1.1.0 h1:f+aAedNJA6uk7+6rXsYBnhdo4Xux7ESLe+kcuVUF5os=
 github.com/peterh/liner v1.1.0/go.mod h1:CRroGNssyjTd/qIG2FyxByd2S8JEAZXBl4qUrZf8GS0=
 github.com/pierrec/lz4/v4 v4.1.17 h1:kV4Ip+/hUBC+8T6+2EgburRtkE9ef4nbY3f4dFhGjMc=
@@ -306,21 +293,13 @@ github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFR
 github.com/rogpeppe/go-internal v1.9.0 h1:73kH8U+JUqXU8lRuOHeVHaa/SZPifC7BkcraZVejAe8=
 github.com/rs/cors v1.8.0 h1:P2KMzcFwrPoSjkF1WLRPsp3UMLyql8L4v9hQpVeK5so=
 github.com/rs/cors v1.8.0/go.mod h1:EBwu+T5AvHOcXwvZIkQFjUN6s8Czyqw12GL/Y0tUyRM=
-github.com/russross/blackfriday v1.5.2/go.mod h1:JO/DiYxRf+HjHt06OyowR9PTA263kcR/rfWxYHBV53g=
 github.com/scylladb/termtables v0.0.0-20191203121021-c4c0b6d42ff4/go.mod h1:C1a7PQSMz9NShzorzCiG2fk9+xuCgLkPeCvMHYR2OWg=
 github.com/segmentio/ksuid v1.0.2 h1:9yBfKyw4ECGTdALaF09Snw3sLJmYIX6AbPJrAy6MrDc=
 github.com/segmentio/ksuid v1.0.2/go.mod h1:BXuJDr2byAiHuQaQtSKoXh1J0YmUDurywOXgB2w+OSU=
 github.com/sirupsen/logrus v1.2.0/go.mod h1:LxeOpSwHxABJmUn/MG1IvRgCAasNZTLOkJPxbbu5VWo=
 github.com/sirupsen/logrus v1.4.2/go.mod h1:tLMulIdttU9McNUspp0xgXVQah82FyeX6MwdIuYE2rE=
 github.com/sirupsen/logrus v1.6.0/go.mod h1:7uNnSEd1DgxDLC74fIahvMZmmYsHGZGEOFrfsX/uA88=
 github.com/spaolacci/murmur3 v0.0.0-20180118202830-f09979ecbc72/go.mod h1:JwIasOWyU6f++ZhiEuf87xNszmSA2myDM2Kzu9HwQUA=
-github.com/spf13/afero v1.1.2/go.mod h1:j4pytiNVoe2o6bmDsKpLACNPDBIoEAkihy7loJ1B0CQ=
-github.com/spf13/cast v1.3.0/go.mod h1:Qx5cxh0v+4UWYiBimWS+eyWzqEqokIECu5etghLkUJE=
-github.com/spf13/cobra v0.0.5/go.mod h1:3K3wKZymM7VvHMDS9+Akkh4K60UwM26emMESw8tLCHU=
-github.com/spf13/jwalterweatherman v1.0.0/go.mod h1:cQK4TGJAtQXfYWX+Ddv3mKDzgVb68N+wFjFa4jdeBTo=
-github.com/spf13/pflag v1.0.3/go.mod h1:DYY7MBk1bdzusC3SYhjObp+wFpr4gzcvqqNjLnInEg4=
-github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
-github.com/spf13/viper v1.3.2/go.mod h1:ZiWeW+zYFKm7srdB9IoDzzZXaJaI5eL9QjNiN/DMA2s=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.1.1/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.4.0 h1:M2gUjqZET1qApGOWNSnZ49BAIMX4F/1plDv3+l31EJ4=
@@ -334,11 +313,9 @@ github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/
 github.com/stretchr/testify v1.8.0 h1:pSgiaMZlXftHpm5L7V1+rVB+AZJydKsMxsQBIJw4PKk=
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
 github.com/ugorji/go v1.1.7/go.mod h1:kZn38zHttfInRq0xu/PH0az30d+z6vm202qpg1oXVMw=
-github.com/ugorji/go/codec v0.0.0-20181204163529-d75b2dcb6bc8/go.mod h1:VFNgLljTbGfSG7qAOspJ7OScBnGdDN/yBr0sguwnwf0=
 github.com/ugorji/go/codec v1.1.7/go.mod h1:Ax+UKWsSmolVDwsd+7N3ZtXu+yMGCf907BLYF3GoBXY=
 github.com/x448/float16 v0.8.4 h1:qLwI1I70+NjRFUR3zs1JPUCgaCXSh3SW62uAKT1mSBM=
 github.com/x448/float16 v0.8.4/go.mod h1:14CWIYCyZA/cWjXOioeEpHeN/83MdbZDRQHoFcYsOfg=
-github.com/xordataexchange/crypt v0.0.3-0.20170626215501-b2862e3d0a77/go.mod h1:aYKd//L2LvnjZzWKhF00oedf4jCCReLcmhLdhm1A27Q=
 github.com/yuin/goldmark v1.1.25/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.1.32/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
@@ -362,7 +339,6 @@ go.uber.org/multierr v1.8.0/go.mod h1:7EAYxJLBy9rStEaz58O2t4Uvip6FSURkq8/ppBp95a
 go.uber.org/zap v1.23.0 h1:OjGQ5KQDEUawVHxNwQgPpiypGHOxo2mNZsOqTak4fFY=
 go.uber.org/zap v1.23.0/go.mod h1:D+nX8jyLsMHMYrln8A0rJjFt/T/9/bGgIhAqxv5URuY=
 golang.org/x/crypto v0.0.0-20180904163835-0709b304e793/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
-golang.org/x/crypto v0.0.0-20181203042331-505ab145d0a9/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20190510104115-cbcb75029529/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20190605123033-f99c8df09eb5/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
@@ -461,7 +437,6 @@ golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5h
 golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20180909124046-d0be0721c37e/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20181116152217-5ac8a444bdc5/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
-golang.org/x/sys v0.0.0-20181205085412-a5c9d58dba9a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190312061237-fead79001313/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=

zed_test.go

@@ -17,7 +17,6 @@ import (
 	"github.com/brimdata/zed/zio"
 	"github.com/brimdata/zed/zio/anyio"
 	"github.com/brimdata/zed/zio/arrowio"
-	"github.com/brimdata/zed/zio/parquetio"
 	"github.com/brimdata/zed/zio/zngio"
 	"github.com/brimdata/zed/ztest"
 	"github.com/stretchr/testify/assert"
@@ -154,13 +153,7 @@ func runOneBoomerang(t *testing.T, format, data string) {
 	if err != nil {
 		if errors.Is(err, arrowio.ErrMultipleTypes) ||
 			errors.Is(err, arrowio.ErrNotRecord) ||
-			errors.Is(err, arrowio.ErrUnsupportedType) ||
-			errors.Is(err, parquetio.ErrEmptyRecordType) ||
-			errors.Is(err, parquetio.ErrNullType) ||
-			errors.Is(err, parquetio.ErrUnionType) ||
-			strings.Contains(err.Error(), "Parquet output encountered non-record value") ||
-			strings.Contains(err.Error(), "Parquet output requires uniform records but multiple types encountered") ||
-			strings.Contains(err.Error(), "column has no name") {
+			errors.Is(err, arrowio.ErrUnsupportedType) {
 			t.Skipf("skipping due to expected error: %s", err)
 		}
 		t.Fatalf("unexpected error writing %s baseline: %s", format, err)

zio/arrowio/writer.go

@@ -35,15 +35,27 @@ var (
 // dictionaries are not part of the Zed data model, write support could be added
 // using a named type.)
 type Writer struct {
+	NewWriterFunc    func(io.Writer, *arrow.Schema) (WriteCloser, error)
 	w                io.WriteCloser
-	writer           *ipc.Writer
+	writer           WriteCloser
 	builder          *array.RecordBuilder
 	unionTagMappings map[zed.Type][]int
 	typ              *zed.TypeRecord
 }
 
+type WriteCloser interface {
+	Write(rec arrow.Record) error
+	Close() error
+}
+
 func NewWriter(w io.WriteCloser) *Writer {
-	return &Writer{w: w, unionTagMappings: map[zed.Type][]int{}}
+	return &Writer{
+		NewWriterFunc: func(w io.Writer, s *arrow.Schema) (WriteCloser, error) {
+			return ipc.NewWriter(w, ipc.WithSchema(s)), nil
+		},
+		w:                w,
+		unionTagMappings: map[zed.Type][]int{},
+	}
 }
 
 func (w *Writer) Close() error {
@@ -78,7 +90,10 @@ func (w *Writer) Write(val *zed.Value) error {
 		schema := arrow.NewSchema(dt.(*arrow.StructType).Fields(), nil)
 		w.builder = array.NewRecordBuilder(memory.DefaultAllocator, schema)
 		w.builder.Reserve(recordBatchSize)
-		w.writer = ipc.NewWriter(w.w, ipc.WithSchema(schema))
+		w.writer, err = w.NewWriterFunc(w.w, schema)
+		if err != nil {
+			return err
+		}
 	} else if w.typ != recType {
 		return fmt.Errorf("%w: %s and %s", ErrMultipleTypes, zson.FormatType(w.typ), zson.FormatType(recType))
 	}