diff --git a/go.mod b/go.mod index 4e31f1d..7d469d2 100644 --- a/go.mod +++ b/go.mod @@ -1,17 +1,58 @@ module github.com/uber/athenadriver -go 1.13 +go 1.22 + +toolchain go1.23.0 require ( github.com/DATA-DOG/go-sqlmock v1.4.1 github.com/aws/aws-sdk-go v1.51.3 + github.com/aws/aws-sdk-go-v2/config v1.27.43 + github.com/aws/aws-sdk-go-v2/service/s3 v1.65.3 github.com/cactus/go-statsd-client/statsd v0.0.0-20200423205355-cb0885a1018c github.com/jedib0t/go-pretty/v6 v6.2.7 - github.com/pkg/errors v0.9.1 // indirect - github.com/stretchr/testify v1.7.0 + github.com/stretchr/testify v1.9.0 github.com/uber-go/tally v3.3.17+incompatible github.com/xwb1989/sqlparser v0.0.0-20180606152119-120387863bf2 go.uber.org/config v1.4.0 go.uber.org/fx v1.12.0 go.uber.org/zap v1.15.0 ) + +require ( + github.com/BurntSushi/toml v1.3.2 // indirect + github.com/aws/aws-sdk-go-v2 v1.32.2 // indirect + github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.6 // indirect + github.com/aws/aws-sdk-go-v2/credentials v1.17.41 // indirect + github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.17 // indirect + github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.21 // indirect + github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.21 // indirect + github.com/aws/aws-sdk-go-v2/internal/ini v1.8.1 // indirect + github.com/aws/aws-sdk-go-v2/internal/v4a v1.3.21 // indirect + github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.12.0 // indirect + github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.4.2 // indirect + github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.12.2 // indirect + github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.18.2 // indirect + github.com/aws/aws-sdk-go-v2/service/sso v1.24.2 // indirect + github.com/aws/aws-sdk-go-v2/service/ssooidc v1.28.2 // indirect + github.com/aws/aws-sdk-go-v2/service/sts v1.32.2 // indirect + github.com/aws/smithy-go v1.22.0 // indirect + github.com/davecgh/go-spew v1.1.1 // indirect + github.com/jmespath/go-jmespath v0.4.0 // indirect + github.com/kr/pretty v0.3.1 // indirect + github.com/mattn/go-runewidth v0.0.13 // indirect + github.com/pkg/errors v0.9.1 // indirect + github.com/pmezard/go-difflib v1.0.0 // indirect + github.com/rivo/uniseg v0.2.0 // indirect + github.com/rogpeppe/go-internal v1.13.1 // indirect + go.uber.org/atomic v1.6.0 // indirect + go.uber.org/dig v1.9.0 // indirect + go.uber.org/multierr v1.5.0 // indirect + golang.org/x/lint v0.0.0-20190930215403-16217165b5de // indirect + golang.org/x/sys v0.26.0 // indirect + golang.org/x/text v0.19.0 // indirect + golang.org/x/tools v0.22.0 // indirect + gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c // indirect + gopkg.in/yaml.v2 v2.4.0 // indirect + gopkg.in/yaml.v3 v3.0.1 // indirect +) diff --git a/go.sum b/go.sum index d550f2d..cf8485a 100644 --- a/go.sum +++ b/go.sum @@ -1,15 +1,49 @@ -github.com/BurntSushi/toml v0.3.1 h1:WXkYYl6Yr3qBf1K79EBnL4mak0OimBfB0XUf9Vl28OQ= github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU= +github.com/BurntSushi/toml v1.3.2 h1:o7IhLm0Msx3BaB+n3Ag7L8EVlByGnpq14C4YWiu/gL8= +github.com/BurntSushi/toml v1.3.2/go.mod h1:CxXYINrC8qIiEnFrOxCa7Jy5BFHlXnUU2pbicEuybxQ= github.com/DATA-DOG/go-sqlmock v1.4.1 h1:ThlnYciV1iM/V0OSF/dtkqWb6xo5qITT1TJBG1MRDJM= github.com/DATA-DOG/go-sqlmock v1.4.1/go.mod h1:f/Ixk793poVmq4qj/V1dPUg2JEAKC73Q5eFN3EC/SaM= -github.com/aws/aws-sdk-go v1.37.32 h1:gLEASuX1phzqb00APUZU/xVIqf13IoA250RlgQ9rz28= -github.com/aws/aws-sdk-go v1.37.32/go.mod h1:hcU610XS61/+aQV88ixoOzUoG7v3b31pl2zKMmprdro= github.com/aws/aws-sdk-go v1.51.3 h1:OqSyEXcJwf/XhZNVpMRgKlLA9nmbo5X8dwbll4RWxq8= github.com/aws/aws-sdk-go v1.51.3/go.mod h1:LF8svs817+Nz+DmiMQKTO3ubZ/6IaTpq3TjupRn3Eqk= -github.com/aws/aws-sdk-go v1.54.19 h1:tyWV+07jagrNiCcGRzRhdtVjQs7Vy41NwsuOcl0IbVI= -github.com/aws/aws-sdk-go v1.54.19/go.mod h1:eRwEWoyTWFMVYVQzKMNHWP5/RV4xIUGMQfXQHfHkpNU= +github.com/aws/aws-sdk-go-v2 v1.32.2 h1:AkNLZEyYMLnx/Q/mSKkcMqwNFXMAvFto9bNsHqcTduI= +github.com/aws/aws-sdk-go-v2 v1.32.2/go.mod h1:2SK5n0a2karNTv5tbP1SjsX0uhttou00v/HpXKM1ZUo= +github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.6 h1:pT3hpW0cOHRJx8Y0DfJUEQuqPild8jRGmSFmBgvydr0= +github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.6.6/go.mod h1:j/I2++U0xX+cr44QjHay4Cvxj6FUbnxrgmqN3H1jTZA= +github.com/aws/aws-sdk-go-v2/config v1.27.43 h1:p33fDDihFC390dhhuv8nOmX419wjOSDQRb+USt20RrU= +github.com/aws/aws-sdk-go-v2/config v1.27.43/go.mod h1:pYhbtvg1siOOg8h5an77rXle9tVG8T+BWLWAo7cOukc= +github.com/aws/aws-sdk-go-v2/credentials v1.17.41 h1:7gXo+Axmp+R4Z+AK8YFQO0ZV3L0gizGINCOWxSLY9W8= +github.com/aws/aws-sdk-go-v2/credentials v1.17.41/go.mod h1:u4Eb8d3394YLubphT4jLEwN1rLNq2wFOlT6OuxFwPzU= +github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.17 h1:TMH3f/SCAWdNtXXVPPu5D6wrr4G5hI1rAxbcocKfC7Q= +github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.16.17/go.mod h1:1ZRXLdTpzdJb9fwTMXiLipENRxkGMTn1sfKexGllQCw= +github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.21 h1:UAsR3xA31QGf79WzpG/ixT9FZvQlh5HY1NRqSHBNOCk= +github.com/aws/aws-sdk-go-v2/internal/configsources v1.3.21/go.mod h1:JNr43NFf5L9YaG3eKTm7HQzls9J+A9YYcGI5Quh1r2Y= +github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.21 h1:6jZVETqmYCadGFvrYEQfC5fAQmlo80CeL5psbno6r0s= +github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.6.21/go.mod h1:1SR0GbLlnN3QUmYaflZNiH1ql+1qrSiB2vwcJ+4UM60= +github.com/aws/aws-sdk-go-v2/internal/ini v1.8.1 h1:VaRN3TlFdd6KxX1x3ILT5ynH6HvKgqdiXoTxAF4HQcQ= +github.com/aws/aws-sdk-go-v2/internal/ini v1.8.1/go.mod h1:FbtygfRFze9usAadmnGJNc8KsP346kEe+y2/oyhGAGc= +github.com/aws/aws-sdk-go-v2/internal/v4a v1.3.21 h1:7edmS3VOBDhK00b/MwGtGglCm7hhwNYnjJs/PgFdMQE= +github.com/aws/aws-sdk-go-v2/internal/v4a v1.3.21/go.mod h1:Q9o5h4HoIWG8XfzxqiuK/CGUbepCJ8uTlaE3bAbxytQ= +github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.12.0 h1:TToQNkvGguu209puTojY/ozlqy2d/SFNcoLIqTFi42g= +github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.12.0/go.mod h1:0jp+ltwkf+SwG2fm/PKo8t4y8pJSgOCO4D8Lz3k0aHQ= +github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.4.2 h1:4FMHqLfk0efmTqhXVRL5xYRqlEBNBiRI7N6w4jsEdd4= +github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.4.2/go.mod h1:LWoqeWlK9OZeJxsROW2RqrSPvQHKTpp69r/iDjwsSaw= +github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.12.2 h1:s7NA1SOw8q/5c0wr8477yOPp0z+uBaXBnLE0XYb0POA= +github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.12.2/go.mod h1:fnjjWyAW/Pj5HYOxl9LJqWtEwS7W2qgcRLWP+uWbss0= +github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.18.2 h1:t7iUP9+4wdc5lt3E41huP+GvQZJD38WLsgVp4iOtAjg= +github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.18.2/go.mod h1:/niFCtmuQNxqx9v8WAPq5qh7EH25U4BF6tjoyq9bObM= +github.com/aws/aws-sdk-go-v2/service/s3 v1.65.3 h1:xxHGZ+wUgZNACQmxtdvP5tgzfsxGS3vPpTP5Hy3iToE= +github.com/aws/aws-sdk-go-v2/service/s3 v1.65.3/go.mod h1:cB6oAuus7YXRZhWCc1wIwPywwZ1XwweNp2TVAEGYeB8= +github.com/aws/aws-sdk-go-v2/service/sso v1.24.2 h1:bSYXVyUzoTHoKalBmwaZxs97HU9DWWI3ehHSAMa7xOk= +github.com/aws/aws-sdk-go-v2/service/sso v1.24.2/go.mod h1:skMqY7JElusiOUjMJMOv1jJsP7YUg7DrhgqZZWuzu1U= +github.com/aws/aws-sdk-go-v2/service/ssooidc v1.28.2 h1:AhmO1fHINP9vFYUE0LHzCWg/LfUWUF+zFPEcY9QXb7o= +github.com/aws/aws-sdk-go-v2/service/ssooidc v1.28.2/go.mod h1:o8aQygT2+MVP0NaV6kbdE1YnnIM8RRVQzoeUH45GOdI= +github.com/aws/aws-sdk-go-v2/service/sts v1.32.2 h1:CiS7i0+FUe+/YY1GvIBLLrR/XNGZ4CtM1Ll0XavNuVo= +github.com/aws/aws-sdk-go-v2/service/sts v1.32.2/go.mod h1:HtaiBI8CjYoNVde8arShXb94UbQQi9L4EMr6D+xGBwo= +github.com/aws/smithy-go v1.22.0 h1:uunKnWlcoL3zO7q+gG2Pk53joueEOsnNB28QdMsmiMM= +github.com/aws/smithy-go v1.22.0/go.mod h1:irrKGvNn1InZwb2d7fkIRNucdfwR8R+Ts3wxYa/cJHg= github.com/cactus/go-statsd-client/statsd v0.0.0-20200423205355-cb0885a1018c h1:HIGF0r/56+7fuIZw2V4isE22MK6xpxWx7BbV8dJ290w= github.com/cactus/go-statsd-client/statsd v0.0.0-20200423205355-cb0885a1018c/go.mod h1:l/bIBLeOl9eX+wxJAzxS4TveKRtAqlyDpHjhkfO0MEI= +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= github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= @@ -21,13 +55,17 @@ github.com/jmespath/go-jmespath v0.4.0/go.mod h1:T8mJZnbsbmF+m6zOOFylbeCJqk5+pHW github.com/jmespath/go-jmespath/internal/testify v1.5.1 h1:shLQSRRSCCPj3f2gpwzGwWFoC7ycTf1rcQZHOlsJ6N8= github.com/jmespath/go-jmespath/internal/testify v1.5.1/go.mod h1:L3OGu8Wl2/fWfCI6z80xFu9LTZmf1ZRjMHUOPmWr69U= github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck= -github.com/kr/pretty v0.1.0 h1:L/CwN0zerZDmRFUapSPitk6f+Q3+0za1rQkzVuMiMFI= github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo= +github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI= +github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE= +github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk= github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ= -github.com/kr/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE= 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/mattn/go-runewidth v0.0.13 h1:lTGmDsbAYt5DmK6OnoV7EuIF1wEIFAcxld6ypU4OSgU= github.com/mattn/go-runewidth v0.0.13/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w= +github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA= github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0= github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4= github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0= @@ -37,16 +75,19 @@ github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZN github.com/rivo/uniseg v0.2.0 h1:S1pD9weZBuJdFmowNwbpi7BJ8TNftyUImj/0WQi72jY= github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc= github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4= +github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs= +github.com/rogpeppe/go-internal v1.13.1 h1:KvO1DLK/DRN07sQ1LQKScxyZJuNnedQ5/wKSR38lUII= +github.com/rogpeppe/go-internal v1.13.1/go.mod h1:uMEvuHeurkdAXX61udpOXGD/AzZDWNMNyH2VO9fmH0o= github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI= github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4= -github.com/stretchr/testify v1.7.0 h1:nwc3DEeHmmLAfoZucVR881uASk0Mfjw8xYJ99tb5CcY= github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg= +github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg= +github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY= github.com/uber-go/tally v3.3.17+incompatible h1:nFHIuW3VQ22wItiE9kPXic8dEgExWOsVOHwpmoIvsMw= github.com/uber-go/tally v3.3.17+incompatible/go.mod h1:YDTIBxdXyOU/sCWilKB4bgyufu1cEi0jdVnRdxvjnmU= github.com/xwb1989/sqlparser v0.0.0-20180606152119-120387863bf2 h1:zzrxE1FKn5ryBNl9eKOeqQ58Y/Qpo3Q9QNxKHX5uzzQ= github.com/xwb1989/sqlparser v0.0.0-20180606152119-120387863bf2/go.mod h1:hzfGeIUDq/j97IG+FhNqkowIyEcD88LrW6fyU3K3WqY= -github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY= go.uber.org/atomic v1.5.0/go.mod h1:sABNBOSYdrvTF6hTgEIbc7YasKWGhgEQZyfxyTvoXHQ= go.uber.org/atomic v1.6.0 h1:Ezj3JGmsOnG1MoRWQkPBsKLe9DwWD9QeXzTRzzldNVk= go.uber.org/atomic v1.6.0/go.mod h1:sABNBOSYdrvTF6hTgEIbc7YasKWGhgEQZyfxyTvoXHQ= @@ -56,7 +97,6 @@ go.uber.org/dig v1.9.0 h1:pJTDXKEhRqBI8W7rU7kwT5EgyRZuSMVSFcZolOvKK9U= go.uber.org/dig v1.9.0/go.mod h1:X34SnWGr8Fyla9zQNO2GSO2D+TIuqB14OS8JhYocIyw= go.uber.org/fx v1.12.0 h1:+1+3Cz9M0dFMPy9SW9XUIUHye8bnPUm7q7DroNGWYG4= go.uber.org/fx v1.12.0/go.mod h1:egT3Kyg1JFYQkvKLZ3EsykxkNrZxgXS+gKoKo7abERY= -go.uber.org/goleak v0.10.0 h1:G3eWbSNIskeRqtsN/1uI5B+eP73y3JUuBsv9AZjehb4= go.uber.org/goleak v0.10.0/go.mod h1:VCZuO8V8mFPlL0F5J5GK1rtHV3DrFcQ1R8ryq7FK0aI= go.uber.org/multierr v1.4.0/go.mod h1:VgVr7evmIr6uPjLBxg28wmKNXyqE9akIJ5XnfpiKl+4= go.uber.org/multierr v1.5.0 h1:KCa4XfM8CWFCpxXRGok+Q0SS/0XBhMDbHHGABQLvD2A= @@ -67,52 +107,26 @@ go.uber.org/zap v1.15.0 h1:ZZCA22JRF2gQE5FoNmhmrf7jeJJ2uhqDUNRYKm8dvmM= go.uber.org/zap v1.15.0/go.mod h1:Mb2vm2krFEG5DV0W9qcHBYFtp/Wku1cvYaqPsS/WYfc= 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 v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto= -golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc= -golang.org/x/crypto v0.14.0/go.mod h1:MVFd36DqK4CsrnJYDkBA3VC4m2GkXAM0PvzMCn4JQf4= golang.org/x/lint v0.0.0-20190930215403-16217165b5de h1:5hukYrvBGR8/eNkX5mdUezrA6JiaEZDtJb9Ei+1LlBs= golang.org/x/lint v0.0.0-20190930215403-16217165b5de/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc= golang.org/x/mod v0.0.0-20190513183733-4bf6d317e70e/go.mod h1:mXi4GBBbnImb6dmsKGUJ2LatrhH/nqhxcFungHvyanc= -golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4= -golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs= +golang.org/x/mod v0.18.0 h1:5+9lSbEzPSdWkH32vYPBwEpX8KwDbM52Ud9xBUvNlb0= +golang.org/x/mod v0.18.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c= golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg= golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg= golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s= -golang.org/x/net v0.0.0-20201110031124-69a78807bb2b h1:uwuIcX0g4Yl1NC5XAz37xsr2lTtcqevgzYNVt49waME= -golang.org/x/net v0.0.0-20201110031124-69a78807bb2b/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU= -golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg= -golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c= -golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs= -golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg= -golang.org/x/net v0.17.0/go.mod h1:NxSsAGuq816PNPmqtQdLE42eU2Fs7NoRIZrHJAlaCOE= golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= -golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= -golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.8.0 h1:3NFvSEYkUoMifnESzZl15y791HH1qU2xm6eCJU5ZPXQ= +golang.org/x/sync v0.8.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk= golang.org/x/sys v0.0.0-20180816055513-1c9583448a9c/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 v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= -golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f h1:+Nyd8tzPX9R7BWHguqsrbFdRx3WQ/1ib8I44HXV5yTA= -golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= -golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= -golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= -golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= -golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= -golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= -golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= -golang.org/x/sys v0.13.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= -golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo= -golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8= -golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k= -golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo= -golang.org/x/term v0.13.0/go.mod h1:LTmsnFJwVN6bCy1rVCoS+qHT1HhALEFxKncY3WNNh4U= +golang.org/x/sys v0.26.0 h1:KHjCJyddX0LoSTb3J+vWpupP9p0oznkqVk/IfjymZbo= +golang.org/x/sys v0.26.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ= golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk= -golang.org/x/text v0.3.3 h1:cokOdA+Jmi5PJGXLlLllQSgYigAEfHXJAERHVMaCc2k= -golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ= -golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ= -golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8= -golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8= -golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE= +golang.org/x/text v0.19.0 h1:kTxAhCbGbxhK0IwgSKiMO5awPoDQ0RpfiVYBfK860YM= +golang.org/x/text v0.19.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY= golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs= golang.org/x/tools v0.0.0-20190621195816-6e04913cbbac/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc= @@ -120,22 +134,22 @@ golang.org/x/tools v0.0.0-20191029041327-9cc4af7d6b2c/go.mod h1:b+2E5dAYhXwXZwtn golang.org/x/tools v0.0.0-20191029190741-b9c20aec41a5/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= golang.org/x/tools v0.0.0-20191030062658-86caa796c7ab/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= golang.org/x/tools v0.0.0-20191104232314-dc038396d1f0/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= -golang.org/x/tools v0.0.0-20191114200427-caa0b0f7d508 h1:0FYNp0PF9kFm/ZUrvcJiQ12IUJJG7iAc6Cu01wbKrbU= golang.org/x/tools v0.0.0-20191114200427-caa0b0f7d508/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= -golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= -golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc= -golang.org/x/tools v0.6.0 h1:BOw41kyTf3PuCW1pVQf8+Cyg8pMlkYB1oo9iJ6D/lKM= -golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU= +golang.org/x/tools v0.22.0 h1:gqSGLZqv+AI9lIQzniJ0nZDRG5GBPsSi+DRNHWNz6yA= +golang.org/x/tools v0.22.0/go.mod h1:aCwcsjqvq7Yqt6TNyX7QMU2enbQ/Gt0bo6krSeEri+c= golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= -gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127 h1:qIbj1fsPNlZgppZ+VLlY7N33q108Sa+fhmuc+sWQYwY= gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= +gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk= +gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q= gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI= gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI= gopkg.in/yaml.v2 v2.2.5/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI= -gopkg.in/yaml.v2 v2.2.8 h1:obN1ZagJSUGI0Ek/LBmuj4SNLPfIny3KsKFopxRdj10= gopkg.in/yaml.v2 v2.2.8/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI= -gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c h1:dUUwHk2QECo/6vqA44rthZ8ie2QXMNeKRTHCNY2nXvo= +gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY= +gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ= gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= +gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= +gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= honnef.co/go/tools v0.0.1-2019.2.3 h1:3JgtbtFHMiCmsznwGVTUWbgGov+pVqnlf1dEJTNAXeM= honnef.co/go/tools v0.0.1-2019.2.3/go.mod h1:a3bituU0lyd329TUQxRnasdCoJDkEUEAqEt0JzvZhAg= diff --git a/go/config.go b/go/config.go index e79565c..ce499b7 100644 --- a/go/config.go +++ b/go/config.go @@ -23,8 +23,8 @@ package athenadriver import ( "net/url" "regexp" - "strings" "strconv" + "strings" "time" ) @@ -56,6 +56,9 @@ var ( "AWS_REGION", "AWS_DEFAULT_REGION", // Only read if AWS_SDK_LOAD_CONFIG is also set } + s3ResultPrefixEnvKey = []string{ + "AWS_S3_ATHENA_RESULT_PREFIX", + } stsRegionalEndpointKey = []string{ "AWS_STS_REGIONAL_ENDPOINTS", } @@ -176,6 +179,57 @@ func (c *Config) GetRegion() string { return GetFromEnvVal(regionEnvKeys) } +// SetS3Region is to set S3 region. +func (c *Config) SetS3Region(o string) error { + if len(o) == 0 { + return ErrConfigRegion + } + c.values.Set("s3_region", o) + return nil +} + +// GetS3Region is getter of S3 region. +func (c *Config) GetS3Region() string { + if val := c.values.Get("s3_region"); val != "" { + return val + } + return GetFromEnvVal(regionEnvKeys) +} + +// SetS3ResultPrefix is to set key prefix for athena result. +func (c *Config) SetS3ResultPrefix(o string) error { + if len(o) == 0 { + return ErrConfigS3ResultPrefix + } + c.values.Set("s3_result_prefix", o) + return nil +} + +// GetS3ResultPrefix is getter of key prefix for athena result. +func (c *Config) GetS3ResultPrefix() string { + if val := c.values.Get("s3_result_prefix"); val != "" { + return val + } + return GetFromEnvVal(s3ResultPrefixEnvKey) +} + +// SetS3OutputBucket is setter for S3 output bucket +func (c *Config) SetS3OutputBucket(o string) error { + if len(o) == 0 { + return ErrConfigS3OutputBucket + } + c.values.Set("s3_output_bucket", o) + return nil +} + +// GetS3OutputBucket is getter of s3 output bucket +func (c *Config) GetS3OutputBucket() string { + if val := c.values.Get("s3_output_bucket"); val != "" { + return val + } + return "" +} + // SetUser is a setter of User. func (c *Config) SetUser(o string) { c.dsn.User = url.UserPassword(o, "") diff --git a/go/custom_csv_reader.go b/go/custom_csv_reader.go new file mode 100644 index 0000000..d65adf0 --- /dev/null +++ b/go/custom_csv_reader.go @@ -0,0 +1,484 @@ +// This file is a modified version of upstream csvReader. Original source: https://cs.opensource.google/go/go/+/refs/tags/go1.23.2:src/encoding/csv/reader.go +// I had to add support for distinguishing between ,"", and ,, as the first is empty string but the second should be treated as nil +// I implemented that by adding IsValueMissing method and isFieldEmpty field + +// Copyright 2011 The Go Authors. All rights reserved. +// Use of this source code is governed by a BSD-style +// license that can be found in the LICENSE file. + +// Package csv reads and writes comma-separated values (CSV) files. +// There are many kinds of CSV files; this package supports the format +// described in RFC 4180, except that [Writer] uses LF +// instead of CRLF as newline character by default. +// +// A csv file contains zero or more records of one or more fields per record. +// Each record is separated by the newline character. The final record may +// optionally be followed by a newline character. +// +// field1,field2,field3 +// +// White space is considered part of a field. +// +// Carriage returns before newline characters are silently removed. +// +// Blank lines are ignored. A line with only whitespace characters (excluding +// the ending newline character) is not considered a blank line. +// +// Fields which start and stop with the quote character " are called +// quoted-fields. The beginning and ending quote are not part of the +// field. +// +// The source: +// +// normal string,"quoted-field" +// +// results in the fields +// +// {`normal string`, `quoted-field`} +// +// Within a quoted-field a quote character followed by a second quote +// character is considered a single quote. +// +// "the ""word"" is true","a ""quoted-field""" +// +// results in +// +// {`the "word" is true`, `a "quoted-field"`} +// +// Newlines and commas may be included in a quoted-field +// +// "Multi-line +// field","comma is ," +// +// results in +// +// {`Multi-line +// field`, `comma is ,`} +package athenadriver + +import ( + "bufio" + "bytes" + "errors" + "fmt" + "io" + "unicode" + "unicode/utf8" +) + +// A ParseError is returned for parsing errors. +// Line and column numbers are 1-indexed. +type ParseError struct { + StartLine int // Line where the record starts + Line int // Line where the error occurred + Column int // Column (1-based byte index) where the error occurred + Err error // The actual error +} + +func (e *ParseError) Error() string { + if e.Err == ErrFieldCount { + return fmt.Sprintf("record on line %d: %v", e.Line, e.Err) + } + if e.StartLine != e.Line { + return fmt.Sprintf("record on line %d; parse error on line %d, column %d: %v", e.StartLine, e.Line, e.Column, e.Err) + } + return fmt.Sprintf("parse error on line %d, column %d: %v", e.Line, e.Column, e.Err) +} + +func (e *ParseError) Unwrap() error { return e.Err } + +// These are the errors that can be returned in [ParseError.Err]. +var ( + ErrBareQuote = errors.New("bare \" in non-quoted-field") + ErrQuote = errors.New("extraneous or missing \" in quoted-field") + ErrFieldCount = errors.New("wrong number of fields") + + // Deprecated: ErrTrailingComma is no longer used. + ErrTrailingComma = errors.New("extra delimiter at end of line") +) + +var errInvalidDelim = errors.New("csv: invalid field or comment delimiter") + +func validDelim(r rune) bool { + return r != 0 && r != '"' && r != '\r' && r != '\n' && utf8.ValidRune(r) && r != utf8.RuneError +} + +// A Reader reads records from a CSV-encoded file. +// +// As returned by [NewReader], a Reader expects input conforming to RFC 4180. +// The exported fields can be changed to customize the details before the +// first call to [Reader.Read] or [Reader.ReadAll]. +// +// The Reader converts all \r\n sequences in its input to plain \n, +// including in multiline field values, so that the returned data does +// not depend on which line-ending convention an input file uses. +type Reader struct { + // Comma is the field delimiter. + // It is set to comma (',') by NewReader. + // Comma must be a valid rune and must not be \r, \n, + // or the Unicode replacement character (0xFFFD). + Comma rune + + // Comment, if not 0, is the comment character. Lines beginning with the + // Comment character without preceding whitespace are ignored. + // With leading whitespace the Comment character becomes part of the + // field, even if TrimLeadingSpace is true. + // Comment must be a valid rune and must not be \r, \n, + // or the Unicode replacement character (0xFFFD). + // It must also not be equal to Comma. + Comment rune + + // FieldsPerRecord is the number of expected fields per record. + // If FieldsPerRecord is positive, Read requires each record to + // have the given number of fields. If FieldsPerRecord is 0, Read sets it to + // the number of fields in the first record, so that future records must + // have the same field count. If FieldsPerRecord is negative, no check is + // made and records may have a variable number of fields. + FieldsPerRecord int + + // If LazyQuotes is true, a quote may appear in an unquoted field and a + // non-doubled quote may appear in a quoted field. + LazyQuotes bool + + // If TrimLeadingSpace is true, leading white space in a field is ignored. + // This is done even if the field delimiter, Comma, is white space. + TrimLeadingSpace bool + + // ReuseRecord controls whether calls to Read may return a slice sharing + // the backing array of the previous call's returned slice for performance. + // By default, each call to Read returns newly allocated memory owned by the caller. + ReuseRecord bool + + // Deprecated: TrailingComma is no longer used. + TrailingComma bool + + r *bufio.Reader + + // numLine is the current line being read in the CSV file. + numLine int + + // offset is the input stream byte offset of the current reader position. + offset int64 + + // rawBuffer is a line buffer only used by the readLine method. + rawBuffer []byte + + // recordBuffer holds the unescaped fields, one after another. + // The fields can be accessed by using the indexes in fieldIndexes. + // E.g., For the row `a,"b","c""d",e`, recordBuffer will contain `abc"de` + // and fieldIndexes will contain the indexes [1, 2, 5, 6]. + recordBuffer []byte + + // fieldIndexes is an index of fields inside recordBuffer. + // The i'th field ends at offset fieldIndexes[i] in recordBuffer. + fieldIndexes []int + + // fieldPositions is an index of field positions for the + // last record returned by Read. + fieldPositions []position + + // records whether value on some index was empty (no quotes between commas like a,,c which Athena uses to denote nil value) + isFieldEmpty []bool + + // lastRecord is a record cache and only used when ReuseRecord == true. + lastRecord []string +} + +// NewReader returns a new Reader that reads from r. +func NewReader(r io.Reader) *Reader { + return &Reader{ + Comma: ',', + r: bufio.NewReader(r), + } +} + +// Read reads one record (a slice of fields) from r. +// If the record has an unexpected number of fields, +// Read returns the record along with the error [ErrFieldCount]. +// If the record contains a field that cannot be parsed, +// Read returns a partial record along with the parse error. +// The partial record contains all fields read before the error. +// If there is no data left to be read, Read returns nil, [io.EOF]. +// If [Reader.ReuseRecord] is true, the returned slice may be shared +// between multiple calls to Read. +func (r *Reader) Read() (record []string, err error) { + if r.ReuseRecord { + record, err = r.readRecord(r.lastRecord) + r.lastRecord = record + } else { + record, err = r.readRecord(nil) + } + return record, err +} + +// FieldPos returns the line and column corresponding to +// the start of the field with the given index in the slice most recently +// returned by [Reader.Read]. Numbering of lines and columns starts at 1; +// columns are counted in bytes, not runes. +// +// If this is called with an out-of-bounds index, it panics. +func (r *Reader) FieldPos(field int) (line, column int) { + if field < 0 || field >= len(r.fieldPositions) { + panic("out of range index passed to FieldPos") + } + p := &r.fieldPositions[field] + return p.line, p.col +} + +// InputOffset returns the input stream byte offset of the current reader +// position. The offset gives the location of the end of the most recently +// read row and the beginning of the next row. +func (r *Reader) InputOffset() int64 { + return r.offset +} + +// pos holds the position of a field in the current line. +type position struct { + line, col int +} + +// ReadAll reads all the remaining records from r. +// Each record is a slice of fields. +// A successful call returns err == nil, not err == [io.EOF]. Because ReadAll is +// defined to read until EOF, it does not treat end of file as an error to be +// reported. +func (r *Reader) ReadAll() (records [][]string, err error) { + for { + record, err := r.readRecord(nil) + if err == io.EOF { + return records, nil + } + if err != nil { + return nil, err + } + records = append(records, record) + } +} + +func (r *Reader) IsValueMissing(idx int) bool { + return r.isFieldEmpty[idx] +} + +// readLine reads the next line (with the trailing endline). +// If EOF is hit without a trailing endline, it will be omitted. +// If some bytes were read, then the error is never [io.EOF]. +// The result is only valid until the next call to readLine. +func (r *Reader) readLine() ([]byte, error) { + line, err := r.r.ReadSlice('\n') + if err == bufio.ErrBufferFull { + r.rawBuffer = append(r.rawBuffer[:0], line...) + for err == bufio.ErrBufferFull { + line, err = r.r.ReadSlice('\n') + r.rawBuffer = append(r.rawBuffer, line...) + } + line = r.rawBuffer + } + readSize := len(line) + if readSize > 0 && err == io.EOF { + err = nil + // For backwards compatibility, drop trailing \r before EOF. + if line[readSize-1] == '\r' { + line = line[:readSize-1] + } + } + r.numLine++ + r.offset += int64(readSize) + // Normalize \r\n to \n on all input lines. + if n := len(line); n >= 2 && line[n-2] == '\r' && line[n-1] == '\n' { + line[n-2] = '\n' + line = line[:n-1] + } + return line, err +} + +// lengthNL reports the number of bytes for the trailing \n. +func lengthNL(b []byte) int { + if len(b) > 0 && b[len(b)-1] == '\n' { + return 1 + } + return 0 +} + +// nextRune returns the next rune in b or utf8.RuneError. +func nextRune(b []byte) rune { + r, _ := utf8.DecodeRune(b) + return r +} + +func (r *Reader) readRecord(dst []string) ([]string, error) { + if r.Comma == r.Comment || !validDelim(r.Comma) || (r.Comment != 0 && !validDelim(r.Comment)) { + return nil, errInvalidDelim + } + + // Read line (automatically skipping past empty lines and any comments). + var line []byte + var errRead error + for errRead == nil { + line, errRead = r.readLine() + if r.Comment != 0 && nextRune(line) == r.Comment { + line = nil + continue // Skip comment lines + } + if errRead == nil && len(line) == lengthNL(line) { + line = nil + continue // Skip empty lines + } + break + } + if errRead == io.EOF { + return nil, errRead + } + + // Parse each field in the record. + var err error + const quoteLen = len(`"`) + commaLen := utf8.RuneLen(r.Comma) + recLine := r.numLine // Starting line for record + r.recordBuffer = r.recordBuffer[:0] + r.fieldIndexes = r.fieldIndexes[:0] + r.fieldPositions = r.fieldPositions[:0] + r.isFieldEmpty = r.isFieldEmpty[:0] + pos := position{line: r.numLine, col: 1} +parseField: + for { + if r.TrimLeadingSpace { + i := bytes.IndexFunc(line, func(r rune) bool { + return !unicode.IsSpace(r) + }) + if i < 0 { + i = len(line) + pos.col -= lengthNL(line) + } + line = line[i:] + pos.col += i + } + if len(line) == 0 || line[0] != '"' { + // Non-quoted string field + i := bytes.IndexRune(line, r.Comma) + field := line + if i >= 0 { + field = field[:i] + } else { + field = field[:len(field)-lengthNL(field)] + } + // Check to make sure a quote does not appear in field. + if !r.LazyQuotes { + if j := bytes.IndexByte(field, '"'); j >= 0 { + col := pos.col + j + err = &ParseError{StartLine: recLine, Line: r.numLine, Column: col, Err: ErrBareQuote} + break parseField + } + } + r.recordBuffer = append(r.recordBuffer, field...) + r.fieldIndexes = append(r.fieldIndexes, len(r.recordBuffer)) + r.fieldPositions = append(r.fieldPositions, pos) + // The length of the field is 0 and there was no quote so it must have been case with ,, which should be interpreted as empty value + r.isFieldEmpty = append(r.isFieldEmpty, len(field) == 0) + if i >= 0 { + line = line[i+commaLen:] + pos.col += i + commaLen + continue parseField + } + break parseField + } else { + // Quoted string field + fieldPos := pos + line = line[quoteLen:] + pos.col += quoteLen + for { + i := bytes.IndexByte(line, '"') + if i >= 0 { + // Hit next quote. + r.recordBuffer = append(r.recordBuffer, line[:i]...) + line = line[i+quoteLen:] + pos.col += i + quoteLen + switch rn := nextRune(line); { + case rn == '"': + // `""` sequence (append quote). + r.recordBuffer = append(r.recordBuffer, '"') + line = line[quoteLen:] + pos.col += quoteLen + case rn == r.Comma: + // `",` sequence (end of field). + line = line[commaLen:] + pos.col += commaLen + r.fieldIndexes = append(r.fieldIndexes, len(r.recordBuffer)) + r.fieldPositions = append(r.fieldPositions, fieldPos) + r.isFieldEmpty = append(r.isFieldEmpty, false) + continue parseField + case lengthNL(line) == len(line): + // `"\n` sequence (end of line). + r.fieldIndexes = append(r.fieldIndexes, len(r.recordBuffer)) + r.fieldPositions = append(r.fieldPositions, fieldPos) + r.isFieldEmpty = append(r.isFieldEmpty, false) + break parseField + case r.LazyQuotes: + // `"` sequence (bare quote). + r.recordBuffer = append(r.recordBuffer, '"') + default: + // `"*` sequence (invalid non-escaped quote). + err = &ParseError{StartLine: recLine, Line: r.numLine, Column: pos.col - quoteLen, Err: ErrQuote} + break parseField + } + } else if len(line) > 0 { + // Hit end of line (copy all data so far). + r.recordBuffer = append(r.recordBuffer, line...) + if errRead != nil { + break parseField + } + pos.col += len(line) + line, errRead = r.readLine() + if len(line) > 0 { + pos.line++ + pos.col = 1 + } + if errRead == io.EOF { + errRead = nil + } + } else { + // Abrupt end of file (EOF or error). + if !r.LazyQuotes && errRead == nil { + err = &ParseError{StartLine: recLine, Line: pos.line, Column: pos.col, Err: ErrQuote} + break parseField + } + r.fieldIndexes = append(r.fieldIndexes, len(r.recordBuffer)) + r.fieldPositions = append(r.fieldPositions, fieldPos) + r.isFieldEmpty = append(r.isFieldEmpty, false) + break parseField + } + } + } + } + if err == nil { + err = errRead + } + + // Create a single string and create slices out of it. + // This pins the memory of the fields together, but allocates once. + str := string(r.recordBuffer) // Convert to string once to batch allocations + dst = dst[:0] + if cap(dst) < len(r.fieldIndexes) { + dst = make([]string, len(r.fieldIndexes)) + } + dst = dst[:len(r.fieldIndexes)] + var preIdx int + for i, idx := range r.fieldIndexes { + dst[i] = str[preIdx:idx] + preIdx = idx + } + + // Check or update the expected fields per record. + if r.FieldsPerRecord > 0 { + if len(dst) != r.FieldsPerRecord && err == nil { + err = &ParseError{ + StartLine: recLine, + Line: recLine, + Column: 1, + Err: ErrFieldCount, + } + } + } else if r.FieldsPerRecord == 0 { + r.FieldsPerRecord = len(dst) + } + return dst, err +} diff --git a/go/errors.go b/go/errors.go index dcaeb40..a59e5e5 100644 --- a/go/errors.go +++ b/go/errors.go @@ -31,6 +31,8 @@ var ( ErrConfigInvalidConfig = errors.New("driver config is invalid") ErrConfigOutputLocation = errors.New("output location must starts with s3") ErrConfigRegion = errors.New("region is required") + ErrConfigS3ResultPrefix = errors.New("S3 result prefix is required") + ErrConfigS3OutputBucket = errors.New("S3 output bucket is required") ErrConfigWGPointer = errors.New("workgroup pointer is nil") ErrConfigAccessIDRequired = errors.New("AWS access ID is required") ErrConfigAccessKeyRequired = errors.New("AWS access Key is required") diff --git a/go/rows.go b/go/rows.go index bbb1c9b..3eed219 100644 --- a/go/rows.go +++ b/go/rows.go @@ -31,6 +31,8 @@ import ( "go.uber.org/zap" + aws_v2_cfg "github.com/aws/aws-sdk-go-v2/config" + "github.com/aws/aws-sdk-go-v2/service/s3" "github.com/aws/aws-sdk-go/service/athena/athenaiface" "github.com/aws/aws-sdk-go/aws" @@ -44,6 +46,7 @@ type Rows struct { queryID string reachedLastPage bool ResultOutput *athena.GetQueryResultsOutput + csvReader *Reader config *Config tracer *DriverTracer pageCount int64 @@ -77,9 +80,76 @@ func NewRows(ctx context.Context, athenaAPI athenaiface.AthenaAPI, queryID strin if err := r.fetchNextPage(nil); err != nil { return nil, err } + + if r.ResultOutput.NextToken == nil || *r.ResultOutput.NextToken == "" { + return &r, nil + } + + csvReader, err := r.DownloadResultFromS3() + if err != nil { + return nil, err + } + + // The first line is just a list of columns, we don't need that + csvReader.Read() + + r.csvReader = csvReader + return &r, nil } +func (r *Rows) DownloadResultFromS3() (*Reader, error) { + cfg, err := aws_v2_cfg.LoadDefaultConfig(context.TODO()) + if err != nil { + return nil, err + } + + cfg.Region = r.config.GetS3Region() + + client := s3.NewFromConfig(cfg) + + bucket := r.config.GetS3OutputBucket() + path := fmt.Sprintf("%s/%s.csv", r.config.GetS3ResultPrefix(), r.queryID) + + output, err := client.GetObject(context.TODO(), &s3.GetObjectInput{ + Bucket: aws.String(bucket), + Key: aws.String(path), + }) + if err != nil { + return nil, err + } + + defer output.Body.Close() + + // Stream the data and monitor size + const maxSize = 100 * 1024 * 1024 // 100MB in bytes + var totalBytes int64 + builder := &strings.Builder{} + buffer := make([]byte, 1024*1024) // 1MB buffer + + for { + n, err := output.Body.Read(buffer) + if err != nil && err != io.EOF { + return nil, fmt.Errorf("error reading object data: %w", err) + } + totalBytes += int64(n) + if totalBytes > maxSize { + return nil, fmt.Errorf("this query generated more than 100MB of data, please please add LIMIT to your query") + } + + // Write to the string builder + builder.Write(buffer[:n]) + + if err == io.EOF { + break + } + } + + reader := NewReader(strings.NewReader(builder.String())) + + return reader, nil +} + // Columns return Columns metadata. func (r *Rows) Columns() []string { var columns []string @@ -105,6 +175,30 @@ func (r *Rows) Next(dest []driver.Value) error { if r.reachedLastPage { return io.EOF } + + // If there is csvReader available, we should use data from there instead + if r.csvReader != nil { + lineData, err := r.csvReader.Read() + if err != nil { + r.reachedLastPage = true + return io.EOF + } + + cur := newRow(len(lineData), lineData) + for i, data := range cur.Data { + if r.csvReader.IsValueMissing(i) { + data.VarCharValue = nil + } + } + + columns := r.ResultOutput.ResultSet.ResultSetMetadata.ColumnInfo + if err := r.convertRow(columns, cur.Data, dest, r.config); err != nil { + return err + } + + return nil + } + if len(r.ResultOutput.ResultSet.Rows) == 0 { if r.ResultOutput.NextToken == nil || *r.ResultOutput.NextToken == "" { // this means we reach the last page - no token and no rows