Merge pull request #98 from opencultureconsulting/felixlohmeier/import-csv-tsv-options-83

Felixlohmeier/import-csv-tsv-options-83

README.md

@@ -10,7 +10,7 @@ Bash script to control OpenRefine via [its HTTP API](https://docs.openrefine.org
   * allows execution of arbitrary bash scripts
   * interactive mode for playing around and debugging
   * your existing OpenRefine data will not be touched
-* import CSV, ~~TSV, line-based TXT, fixed-width TXT, JSON or XML~~ (and specify input options)
+* import CSV, TSV, ~~line-based TXT, fixed-width TXT, JSON or XML~~ (and specify input options)
   * supports stdin, multiple files and URLs
 * transform data by providing an [undo/redo](https://docs.openrefine.org/manual/running#history-undoredo) JSON file
   * orcli calls specific endpoints for each operation to provide improved error handling and logging

src/bashly.yml

@@ -19,6 +19,7 @@ examples:
   - orcli transform "duplicates" "https://git.io/fj5ju"
   - orcli export tsv "duplicates"
   - orcli export tsv "duplicates" --output "duplicates.tsv"
+  - orcli delete "duplicates"
   - orcli run --interactive
   - |-
     orcli run << EOF
@@ -36,19 +37,23 @@ commands:
   - name: delete
     help: delete OpenRefine project
     args:
-      - name: project
+      - &project
+        name: project
         help: project name or id
         required: true
     flags:
       - long: --force
         short: -f
         help: delete all projects with the same name
-      - long: --quiet
+      - &quiet
+        long: --quiet
         short: -q
         help: suppress log output, print errors only
     examples:
       - orcli delete "duplicates"
+      - orcli delete "duplicates" --force
       - orcli delete 1234567890123
+      - for p in $(orcli list); do orcli delete ${p:0:13}; done
 
   - name: import
     help: commands to create OpenRefine projects from files or URLs
@@ -57,68 +62,137 @@ commands:
       - name: csv
         help: import character-separated values (CSV)
         args:
-          - name: file
+          - &file
+            name: file
             help: Path to one or more files or URLs. When FILE is -, read standard input.
             default: "-"
             repeatable: true
         flags:
-          - long: --separator
+          - &separator
+            long: --separator
             help: character(s) that separates columns
             arg: separator
             default: ","
-          - long: --encoding
+          - &blankCellsAsStrings
+            long: --blankCellsAsStrings
+            help: store blank cells as empty strings instead of nulls
+          - &columnNames
+            long: --columnNames
+            help: |-
+              set column names (comma separated)
+              hint: add --ignoreLines 1 to overwrite existing header row
+            arg: columnNames
+            conflicts: [--headerLines]
+          - &encoding_import
+            long: --encoding
             help: set character encoding
             arg: encoding
-          - long: --trimStrings
+          - &guessCellValueTypes
+            long: --guessCellValueTypes
+            help: attempt to parse cell text into numbers
+          - &headerLines
+            long: --headerLines
+            help: parse x line(s) as column headers
+            arg: headerLines
+            default: "1"
+            conflicts: [--columnNames]
+          - &ignoreLines
+            long: --ignoreLines
+            help: ignore first x line(s) at beginning of file
+            arg: ignoreLines
+            default: "-1"
+          - &ignoreQuoteCharacter
+            long: --ignoreQuoteCharacter
+            help: do not use any quote character to enclose cells containing column separators
+          - &includeFileSources
+            long: --includeFileSources
+            help: add column with file source
+          - &includeArchiveFileName
+            long: --includeArchiveFileName
+            help: add column with archive file name
+          - &limit
+            long: --limit
+            help: load at most x row(s) of data
+            arg: limit
+            default: "-1"
+          - &quoteCharacter
+            long: --quoteCharacter
+            help: quote character to enclose cells containing column separators
+            arg: quoteCharacter
+            default: '\\\"'
+          - &skipBlankRows
+            long: --skipBlankRows
+            help: do not store blank rows
+          - &skipDataLines
+            long: --skipDataLines
+            help: discard initial x row(s) of data
+            arg: skipDataLines
+            default: "0"
+          - &trimStrings
+            long: --trimStrings
             help: trim leading & trailing whitespace from strings
-          - long: --projectName
+          - &projectName
+            long: --projectName
             arg: projectName
             help: set a name for the OpenRefine project
-          - long: --quiet
+          - &projectTags
-            short: -q
+            long: --projectTags
-            help: suppress log output, print errors only
+            help: set project tags (comma separated)
+            arg: projectTags
+          - *quiet
         examples:
           - orcli import csv "file"
           - orcli import csv "file1" "file2"
-          - cat "file" | orcli import csv
+          - head -n 100 "file" | orcli import csv
           - orcli import csv "https://git.io/fj5hF"
           - |-
             orcli import csv "file" \\\\
               --separator ";" \\\\
+              --columnNames "foo,bar,baz" \\\\
+              --ignoreLines 1 \\\\
               --encoding "ISO-8859-1" \\\\
+              --limit 100 \\\\
               --trimStrings \\\\
               --projectName "duplicates"
+              --projectTags "test,urgent"
 
       - name: tsv
         help: import tab-separated values (TSV)
         args:
-          - name: file
+          - *file
-            help: Path to one or more files or URLs. When FILE is -, read standard input.
-            default: "-"
-            repeatable: true
         flags:
-          - long: --encoding
+          - *blankCellsAsStrings
-            help: set character encoding
+          - *columnNames
-            arg: encoding
+          - *encoding_import
-          - long: --trimStrings
+          - *guessCellValueTypes
-            help: trim leading & trailing whitespace from strings
+          - *headerLines
-          - long: --projectName
+          - *ignoreLines
-            arg: projectName
+          - *ignoreQuoteCharacter
-            help: set a name for the OpenRefine project
+          - *includeFileSources
-          - long: --quiet
+          - *includeArchiveFileName
-            short: -q
+          - *limit
-            help: suppress log output, print errors only
+          - *quoteCharacter
+          - *skipBlankRows
+          - *skipDataLines
+          - *trimStrings
+          - *projectName
+          - *projectTags
+          - *quiet
         examples:
           - orcli import tsv "file"
           - orcli import tsv "file1" "file2"
-          - cat "file" | orcli import tsv
+          - head -n 100 "file" | orcli import tsv
           - orcli import tsv "https://git.io/fj5hF"
           - |-
             orcli import tsv "file" \\\\
               --separator ";" \\\\
+              --columnNames "foo,bar,baz" \\\\
+              --ignoreLines 1 \\\\
               --encoding "ISO-8859-1" \\\\
+              --limit 100 \\\\
               --trimStrings \\\\
               --projectName "duplicates"
+              --projectTags "test,urgent"
 
   - name: list
     help: list projects on OpenRefine server
@@ -126,12 +200,11 @@ commands:
   - name: info
     help: show OpenRefine project's metadata
     args:
-      - name: project
+      - *project
-        help: project name or id
-        required: true
     examples:
       - orcli info "duplicates"
       - orcli info 1234567890123
+      - orcli info "duplicates" | jq -r .columns[]
 
   - name: test
     help: run functional tests on tmp OpenRefine workspace
@@ -139,17 +212,10 @@ commands:
   - name: transform
     help: apply undo/redo JSON file(s) to an OpenRefine project
     args:
-      - name: project
+      - *project
-        help: project name or id
+      - *file
-        required: true
-      - name: file
-        help: Path to one or more files or URLs containing OpenRefine's undo/redo operation history in JSON format. When FILE is -, read standard input.
-        default: "-"
-        repeatable: true
     flags:
-      - long: --quiet
+      - *quiet
-        short: -q
-        help: suppress log output, print errors only
     examples:
       - orcli transform "duplicates" "history.json"
       - cat "history.json" | orcli transform "duplicates"
@@ -163,31 +229,27 @@ commands:
       - name: tsv
         help: export tab-separated values (TSV)
         args:
-          - name: project
+          - *project
-            help: project name or id
-            required: true
         flags:
-          - long: --output
+          - &output
+            long: --output
             help: Write to file instead of stdout
             arg: file
-          - long: --encoding
+          - &encoding_export
+            long: --encoding
             help: set character encoding
             arg: encoding
             default: "UTF-8"
-          - long: --quiet
+          - *quiet
-            short: -q
-            help: suppress log output, print errors only
         examples:
           - orcli export tsv "duplicates"
           - orcli export tsv "duplicates" --output "duplicates.tsv"
+          - orcli export tsv "duplicates" --encoding "ISO-8859-1"
 
   - name: run
     help: run tmp OpenRefine workspace and execute shell script(s)
     args:
-      - name: file
+      - *file
-        help: Path to one or more files. When FILE is -, read standard input.
-        default: "-"
-        repeatable: true
     flags:
       - long: --memory
         help: maximum RAM for OpenRefine java heap space
@@ -199,9 +261,7 @@ commands:
         default: "3333"
       - long: --interactive
         help: do not exit on error and keep bash shell open
-      - long: --quiet
+      - *quiet
-        short: -q
-        help: suppress log output, print errors only
     examples:
       - orcli run --interactive
       - |-

src/import_csv_command.sh

@@ -1,15 +1,13 @@
-# shellcheck shell=bash
+# shellcheck shell=bash disable=SC2154
 
 # call init_import function to eval args and to set basic post data
 init_import
 
 # check if stdin is present if selected
-if [[ ${args[file]} == '-' ]] || [[ ${args[file]} == '"-"' ]]; then
+if [[ ${file} == '-' ]] && ! read -u 0 -t 0; then
-    if ! read -u 0 -t 0; then
     orcli_import_csv_usage
     exit 1
 fi
-fi
 
 # assemble specific post data (some options require json format)
 data+=("format=text/line-based/*sv")
@@ -19,9 +17,67 @@ if [[ ${args[--encoding]} ]]; then
     options+=', '
     options+="\"encoding\": \"${args[--encoding]}\""
 fi
+if [[ ${args[--blankCellsAsStrings]} ]]; then
+    options+=', '
+    options+='"storeBlankCellsAsNulls": false'
+fi
+if [[ ${args[--columnNames]} ]]; then
+    IFS=',' read -ra columnNames <<< "${args[--columnNames]}"
+    options+=', '
+    options+="\"columnNames\": [ $(printf ',"'%s'"' "${columnNames[@]}" | cut -c2-) ]"
+fi
+if [[ ${args[--guessCellValueTypes]} ]]; then
+    options+=', '
+    options+='"guessCellValueTypes": true'
+fi
+if [[ ${args[--headerLines]} ]]; then
+    options+=', '
+    options+="\"headerLines\": ${args[--headerLines]}"
+fi
+if [[ ${args[--ignoreLines]} ]]; then
+    options+=', '
+    options+="\"ignoreLines\": ${args[--ignoreLines]}"
+fi
+if [[ ${args[--ignoreQuoteCharacter]} ]]; then
+    options+=', '
+    options+='"processQuotes": false'
+fi
+if [[ ${args[--includeFileSources]} ]]; then
+    options+=', '
+    options+='includeFileSources: true'
+fi
+if [[ ${args[--includeArchiveFileName]} ]]; then
+    options+=', '
+    options+='"includeArchiveFileName": true'
+fi
+if [[ ${args[--limit]} ]]; then
+    options+=', '
+    options+="\"limit\": ${args[--limit]}"
+fi
+if [[ ${args[--projectName]} ]]; then
+    options+=', '
+    options+="\"projectName\": \"${args[--projectName]}\""
+fi
+if [[ ${args[--quoteCharacter]} ]]; then
+    options+=', '
+    options+="\"quoteCharacter\": \"${args[--quoteCharacter]}\""
+fi
+if [[ ${args[--skipBlankRows]} ]]; then
+    options+=', '
+    options+='"storeBlankRows": false'
+fi
+if [[ ${args[--skipDataLines]} ]]; then
+    options+=', '
+    options+="\"skipDataLines\": ${args[--skipDataLines]}"
+fi
 if [[ ${args[--trimStrings]} ]]; then
     options+=', '
-    options+="\"trimStrings\": true"
+    options+='"trimStrings": true'
+fi
+if [[ ${args[--projectTags]} ]]; then
+    IFS=',' read -ra projectTags <<< "${args[--projectTags]}"
+    options+=', '
+    options+="\"projectTags\": [ $(printf ',"'%s'"' "${projectTags[@]}" | cut -c2-) ]"
 fi
 options+=' }'
 data+=("options=${options}")

src/import_tsv_command.sh

@@ -1,15 +1,13 @@
-# shellcheck shell=bash
+# shellcheck shell=bash disable=SC2154
 
 # call init_import function to eval args and to set basic post data
 init_import
 
 # check if stdin is present if selected
-if [[ ${args[file]} == '-' ]] || [[ ${args[file]} == '"-"' ]]; then
+if [[ ${file} == '-' ]] && ! read -u 0 -t 0; then
-    if ! read -u 0 -t 0; then
     orcli_import_tsv_usage
     exit 1
 fi
-fi
 
 # assemble specific post data (some options require json format)
 data+=("format=text/line-based/*sv")
@@ -19,9 +17,67 @@ if [[ ${args[--encoding]} ]]; then
     options+=', '
     options+="\"encoding\": \"${args[--encoding]}\""
 fi
+if [[ ${args[--blankCellsAsStrings]} ]]; then
+    options+=', '
+    options+='"storeBlankCellsAsNulls": false'
+fi
+if [[ ${args[--columnNames]} ]]; then
+    IFS=',' read -ra columnNames <<< "${args[--columnNames]}"
+    options+=', '
+    options+="\"columnNames\": [ $(printf ',"'%s'"' "${columnNames[@]}" | cut -c2-) ]"
+fi
+if [[ ${args[--guessCellValueTypes]} ]]; then
+    options+=', '
+    options+='"guessCellValueTypes": true'
+fi
+if [[ ${args[--headerLines]} ]]; then
+    options+=', '
+    options+="\"headerLines\": ${args[--headerLines]}"
+fi
+if [[ ${args[--ignoreLines]} ]]; then
+    options+=', '
+    options+="\"ignoreLines\": ${args[--ignoreLines]}"
+fi
+if [[ ${args[--ignoreQuoteCharacter]} ]]; then
+    options+=', '
+    options+='"processQuotes": false'
+fi
+if [[ ${args[--includeFileSources]} ]]; then
+    options+=', '
+    options+='includeFileSources: true'
+fi
+if [[ ${args[--includeArchiveFileName]} ]]; then
+    options+=', '
+    options+='"includeArchiveFileName": true'
+fi
+if [[ ${args[--limit]} ]]; then
+    options+=', '
+    options+="\"limit\": ${args[--limit]}"
+fi
+if [[ ${args[--projectName]} ]]; then
+    options+=', '
+    options+="\"projectName\": \"${args[--projectName]}\""
+fi
+if [[ ${args[--quoteCharacter]} ]]; then
+    options+=', '
+    options+="\"quoteCharacter\": \"${args[--quoteCharacter]}\""
+fi
+if [[ ${args[--skipBlankRows]} ]]; then
+    options+=', '
+    options+='"storeBlankRows": false'
+fi
+if [[ ${args[--skipDataLines]} ]]; then
+    options+=', '
+    options+="\"skipDataLines\": ${args[--skipDataLines]}"
+fi
 if [[ ${args[--trimStrings]} ]]; then
     options+=', '
-    options+="\"trimStrings\": true"
+    options+='"trimStrings": true'
+fi
+if [[ ${args[--projectTags]} ]]; then
+    IFS=',' read -ra projectTags <<< "${args[--projectTags]}"
+    options+=', '
+    options+="\"projectTags\": [ $(printf ',"'%s'"' "${projectTags[@]}" | cut -c2-) ]"
 fi
 options+=' }'
 data+=("options=${options}")

src/lib/init_import.sh

@@ -1,9 +1,8 @@
 # common import tasks to support multiple files and URLs
-# shellcheck shell=bash
+# shellcheck shell=bash disable=SC2154
 function init_import() {
-    local files file
     # catch args, convert the space delimited string to an array
-    files=()
+    local files=()
     eval "files=(${args[file]})"
     # create tmp directory
     tmpdir="$(mktemp -d)"
@@ -14,7 +13,7 @@ function init_import() {
             if ! curl -fs --location "${files[$i]}" >"${tmpdir}/${files[$i]//[^A-Za-z0-9._-]/_}"; then
                 error "download of ${files[$i]} failed!"
             fi
-            files[$i]="${tmpdir}/${files[$i]//[^A-Za-z0-9._-]/_}"
+            files[i]="${tmpdir}/${files[$i]//[^A-Za-z0-9._-]/_}"
         fi
     done
     # read pipes if name starts with /dev/fd
@@ -23,7 +22,7 @@ function init_import() {
             if ! cat "${files[$i]}" >"${tmpdir}/${files[$i]//[^A-Za-z0-9._-]/_}"; then
                 error "reading of ${files[$i]} failed!"
             fi
-            files[$i]="${tmpdir}/${files[$i]//[^A-Za-z0-9._-]/_}"
+            files[i]="${tmpdir}/${files[$i]//[^A-Za-z0-9._-]/_}"
         fi
     done
     # create a zip archive if there are multiple files
@@ -35,23 +34,4 @@ function init_import() {
     else
         file="${files[0]}"
     fi
-    # basic post data
-    if [[ ${file} == "-" ]]; then
-        data+=("project-file=@-")
-    else
-        if ! path=$(readlink -e "${file}"); then
-            error "cannot open ${file} (no such file)!"
-        fi
-        data+=("project-file=@${path}")
-    fi
-    if [[ ${args[--projectName]} ]]; then
-        data+=("project-name=${args[--projectName]}")
-    else
-        if [[ ${file} == "-" ]]; then
-            name="Untitled"
-        else
-            name="$(basename "${path}" | tr '.' ' ')"
-        fi
-        data+=("project-name=${name}")
-    fi
 }

src/lib/post_export.sh

@@ -2,18 +2,18 @@
 # shellcheck shell=bash disable=SC2154
 function post_export() {
     local curloptions
-    # post
     mapfile -t curloptions < <(for d in "$@"; do
         echo "--data"
         echo "$d"
     done)
+    # support file output
     if [[ ${args[--output]} ]]; then
         if ! mkdir -p "$(dirname "${args[--output]}")"; then
             error "unable to create parent directory for ${args[--output]}"
         fi
-        curloptions+=("--output")
+        curloptions+=("--output" "${args[--output]}")
-        curloptions+=("${args[--output]}")
     fi
+    # post
     if ! curl -fs "${curloptions[@]}" "${OPENREFINE_URL}/command/core/export-rows"; then
         error "exporting ${args[project]} failed!"
     else

src/lib/post_import.sh

@@ -1,15 +1,31 @@
 # post to create-project endpoint and validate
 # shellcheck shell=bash disable=SC2154
 function post_import() {
-    local curloptions
+    local curloptions projectid projectname rows
-    local projectid
-    local projectname
-    local rows
-    # post
     mapfile -t curloptions < <(for d in "$@"; do
-        echo "--form"
+        echo "--form-string"
         echo "$d"
     done)
+    # basic post data
+    if [[ ${file} == "-" ]]; then
+        curloptions+=("--form" "project-file=@-")
+    else
+        if ! path=$(readlink -e "${file}"); then
+            error "cannot open ${file} (no such file)!"
+        fi
+        curloptions+=("--form" "project-file=@${path}")
+    fi
+    if [[ ${args[--projectName]} ]]; then
+        curloptions+=("--form-string" "project-name=${args[--projectName]}")
+    else
+        if [[ ${file} == "-" ]]; then
+            name="Untitled"
+        else
+            name="$(basename "${path}" | tr '.' ' ')"
+        fi
+        curloptions+=("--form-string" "project-name=${name}")
+    fi
+    # post
     if ! redirect_url="$(curl -fs --write-out "%{redirect_url}\n" "${curloptions[@]}" "${OPENREFINE_URL}/command/core/create-project-from-upload$(get_csrf)")"; then
         error "importing ${args[file]} failed!"
     fi

src/lib/send_completions.sh

@@ -35,11 +35,11 @@ send_completions() {
   echo $'      ;;'
   echo $''
   echo $'    \'import csv\'*)'
-  echo $'      while read -r; do COMPREPLY+=( "$REPLY" ); done < <( compgen -W "$(_orcli_completions_filter "--encoding --help --projectName --quiet --separator --trimStrings -h -q")" -- "$cur" )'
+  echo $'      while read -r; do COMPREPLY+=( "$REPLY" ); done < <( compgen -W "$(_orcli_completions_filter "--blankCellsAsStrings --columnNames --encoding --guessCellValueTypes --headerLines --help --ignoreLines --ignoreQuoteCharacter --includeArchiveFileName --includeFileSources --limit --projectName --projectTags --quiet --quoteCharacter --separator --skipBlankRows --skipDataLines --trimStrings -h -q")" -- "$cur" )'
   echo $'      ;;'
   echo $''
   echo $'    \'import tsv\'*)'
-  echo $'      while read -r; do COMPREPLY+=( "$REPLY" ); done < <( compgen -W "$(_orcli_completions_filter "--encoding --help --projectName --quiet --trimStrings -h -q")" -- "$cur" )'
+  echo $'      while read -r; do COMPREPLY+=( "$REPLY" ); done < <( compgen -W "$(_orcli_completions_filter "--blankCellsAsStrings --columnNames --encoding --guessCellValueTypes --headerLines --help --ignoreLines --ignoreQuoteCharacter --includeArchiveFileName --includeFileSources --limit --projectName --projectTags --quiet --quoteCharacter --skipBlankRows --skipDataLines --trimStrings -h -q")" -- "$cur" )'
   echo $'      ;;'
   echo $''
   echo $'    \'export tsv\'*)'

tests/data/example-iso-8859-1.csv

@@ -0,0 +1,4 @@
+a,b,c
+1,2,3
+ה,י,‗
+$,\,'

tests/data/example-separator.csv

@@ -0,0 +1,4 @@
+a; b; c
+1; 2; 3
+0; 0; 0
+$; \; '

tests/delete.sh

@@ -10,20 +10,19 @@ trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
 cp data/example.csv "${tmpdir}/${t}.csv"
 
 # assertion (empty file)
-cat << "DATA" > "${tmpdir}/${t}.assert"
+touch "${tmpdir}/${t}.assert"
-DATA
 
 # action
 cd "${tmpdir}" || exit 1
-orcli import csv "${t}.csv"
+orcli import csv "${t}.csv" --projectName "${t}"
-orcli list | grep "${t} csv"
+orcli list | grep "${t}"
-orcli delete "${t} csv"
+orcli delete "${t}"
-orcli list | grep "${t} csv" > "${t}.output" || exit 0
+orcli list | grep "${t}" > "${t}.output" || exit 0
-orcli import csv "${t}.csv"
+orcli import csv "${t}.csv" --projectName "${t}"
-orcli import csv "${t}.csv"
+orcli import csv "${t}.csv" --projectName "${t}"
-orcli list | grep "${t} csv"
+orcli list | grep "${t}"
-orcli delete --force "${t} csv"
+orcli delete --force "${t}"
-orcli list | grep "${t} csv" >> "${t}.output" || exit 0
+orcli list | grep "${t}" >> "${t}.output" || exit 0
 
 # test
 diff -u "${t}.assert" "${t}.output"

tests/export-tsv.sh

@@ -14,8 +14,8 @@ cp data/example.tsv "${tmpdir}/${t}.assert"
 
 # action
 cd "${tmpdir}" || exit 1
-orcli import csv "${t}.csv"
+orcli import csv "${t}.csv" --projectName "${t}"
-orcli export tsv "${t} csv" --output "${t}.output"
+orcli export tsv "${t}" --output "${t}.output"
 
 # test
 diff -u "${t}.assert" "${t}.output"

tests/import-csv-blankCellsAsStrings.sh

@@ -0,0 +1,49 @@
+#!/bin/bash
+
+t="import-csv-blankCellsAsStrings"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cat << "DATA" > "${tmpdir}/${t}.csv"
+a,b,c
+1,2,3
+0,,0
+$,\,'
+DATA
+
+cat << "DATA" > "${tmpdir}/${t}.transform"
+[
+  {
+    "op": "core/text-transform",
+    "engineConfig": {
+      "facets": [],
+      "mode": "row-based"
+    },
+    "columnName": "b",
+    "expression": "grel:isNull(value)",
+    "onError": "keep-original",
+    "repeat": false,
+    "repeatCount": 10
+  }
+]
+DATA
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+a	b	c
+1	false	3
+0	false	0
+$	false	'
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}.csv" --projectName "${t}" --blankCellsAsStrings
+orcli transform "${t}" "${tmpdir}/${t}.transform"
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-columnNames.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+
+t="import-csv-columnNames"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cp data/example.csv "${tmpdir}/${t}.csv"
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+foo	bar	baz
+a	b	c
+1	2	3
+0	0	0
+$	\	'
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}.csv" --projectName "${t}" --columnNames "foo,bar,baz"
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-encoding.sh

@@ -0,0 +1,26 @@
+#!/bin/bash
+
+t="import-csv-encoding"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cp data/example-iso-8859-1.csv "${tmpdir}/${t}.csv"
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+a	b	c
+1	2	3
+ä	é	ß
+$	\	'
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}.csv" --projectName "${t}" --encoding "ISO-8859-1"
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-guessCellValueTypes.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+
+t="import-csv-guessCellValueTypes"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cat << "DATA" > "${tmpdir}/${t}.csv"
+a,b,c
+1,2,3
+01,02,03
+$,\,'
+DATA
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+a	b	c
+1	2	3
+1	2	3
+$	\	'
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}.csv" --projectName "${t}" --guessCellValueTypes
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-headerLines.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+
+t="import-csv-headerLines"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cp data/example.csv "${tmpdir}/${t}.csv"
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+Column 1	Column 2	Column 3
+a	b	c
+1	2	3
+0	0	0
+$	\	'
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}.csv" --projectName "${t}" --headerLines 0
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-ignoreLines.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+
+t="import-csv-ignoreLines"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cp data/example.csv "${tmpdir}/${t}.csv"
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+1	2	3
+0	0	0
+$	\	'
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}.csv" --projectName "${t}" --ignoreLines 1
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-ignoreQuoteCharacter.sh

@@ -0,0 +1,32 @@
+#!/bin/bash
+
+t="import-csv-ignoreQuoteCharacter"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cat << "DATA" > "${tmpdir}/${t}.csv"
+a,b,c
+1,"2,0",3
+0,0,0
+$,\,'
+DATA
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+a	b	c	Column 4
+1	2	0	3
+0	0	0	
+$	\	'	
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+# OpenRefine 4.x fails without headerLines manually set
+orcli import csv "${t}.csv" --projectName "${t}" --ignoreQuoteCharacter --headerLines 1
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-includeArchiveFileName.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+
+t="import-csv-includeArchiveFileName"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cp data/example.csv "${tmpdir}/${t}-1.csv"
+cp data/example.csv "${tmpdir}/${t}-2.csv"
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+Archive	a	b	c
+Untitled.zip	1	2	3
+Untitled.zip	0	0	0
+Untitled.zip	$	\	'
+Untitled.zip	1	2	3
+Untitled.zip	0	0	0
+Untitled.zip	$	\	'
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}-1.csv" "${t}-2.csv" --projectName "${t}" --includeArchiveFileName
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-includeFileSources.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+
+t="import-csv-includeFileSources"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cp data/example.csv "${tmpdir}/${t}-1.csv"
+cp data/example.csv "${tmpdir}/${t}-2.csv"
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+File	a	b	c
+import-csv-includeFileSources-1.csv	1	2	3
+import-csv-includeFileSources-1.csv	0	0	0
+import-csv-includeFileSources-1.csv	$	\	'
+import-csv-includeFileSources-2.csv	1	2	3
+import-csv-includeFileSources-2.csv	0	0	0
+import-csv-includeFileSources-2.csv	$	\	'
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}-1.csv" "${t}-2.csv" --projectName "${t}" --includeFileSources
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-limit.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+
+t="import-csv-limit"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cp data/example.csv "${tmpdir}/${t}.csv"
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+a	b	c
+1	2	3
+0	0	0
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}.csv" --projectName "${t}" --limit 2
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-projectTags.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+
+t="import-csv-projectTags"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cp data/example.csv "${tmpdir}/${t}.csv"
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+foo
+bar
+baz
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}.csv" --projectName "${t}" --projectTags "foo,bar,baz"
+orcli info "${t}" | jq -r .tags[] > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-quiet.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+
+t="import-csv-quiet"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cp data/example.csv "${tmpdir}/${t}.csv"
+
+# assertion (empty file)
+touch "${tmpdir}/${t}.assert"
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}.csv" --projectName "${t}" --quiet &> "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-quoteCharacter.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+
+t="import-csv-quoteCharacter"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cat << "DATA" > "${tmpdir}/${t}.csv"
+a,b,c
+1,%2,0%,3
+0,0,0
+$,\,'
+DATA
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+a	b	c
+1	2,0	3
+0	0	0
+$	\	'
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}.csv" --projectName "${t}" --quoteCharacter "%"
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-separator.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+
+t="import-csv-separator"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cp data/example-separator.csv "${tmpdir}/${t}.csv"
+
+# assertion
+cp data/example.tsv "${tmpdir}/${t}.assert"
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}.csv" --projectName "${t}" --separator "; "
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-skipBlankRows.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+
+t="import-csv-skipBlankRows"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cat << "DATA" > "${tmpdir}/${t}.csv"
+a,b,c
+1,2,3
+,,
+$,\,'
+DATA
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+a	b	c
+1	2	3
+$	\	'
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}.csv" --projectName "${t}" --skipBlankRows
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-skipDataLines.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+
+t="import-csv-skipDataLines"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cat << "DATA" > "${tmpdir}/${t}.csv"
+a,b,c
+1,2,3
+0,0,0
+$,\,'
+DATA
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+a	b	c
+0	0	0
+$	\	'
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}.csv" --projectName "${t}" --skipDataLines 1
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-trimStrings.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+
+t="import-csv-trimStrings"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cat << "DATA" > "${tmpdir}/${t}.csv"
+a,b,c
+1 , 2 , 3
+0,0,0
+$,\,'
+DATA
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+a	b	c
+1	2	3
+0	0	0
+$	\	'
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}.csv" --projectName "${t}" --trimStrings
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv-unicode.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+
+t="import-csv-unicode biểu tượng cảm xúc ⛲"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cat << "DATA" > "${tmpdir}/${t}.csv"
+⌨,code,meaning
+⛲,1F347,FOUNTAIN
+⛳,1F349,FLAG IN HOLE
+⛵,1F352,SAILBOAT
+DATA
+
+# assertion
+cat << "DATA" > "${tmpdir}/${t}.assert"
+⌨	code	meaning
+⛲	1F347	FOUNTAIN
+⛳	1F349	FLAG IN HOLE
+⛵	1F352	SAILBOAT
+DATA
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import csv "${t}.csv" --projectName "${t}"
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/import-csv.sh

@@ -14,8 +14,8 @@ cp data/example.tsv "${tmpdir}/${t}.assert"
 
 # action
 cd "${tmpdir}" || exit 1
-orcli import csv "${t}.csv"
+orcli import csv "${t}.csv" --projectName "${t}"
-orcli export tsv "${t} csv" > "${t}.output"
+orcli export tsv "${t}" > "${t}.output"
 
 # test
 diff -u "${t}.assert" "${t}.output"

tests/import-tsv.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+
+t="import-tsv"
+
+# create tmp directory
+tmpdir="$(mktemp -d)"
+trap '{ rm -rf "${tmpdir}"; }' 0 2 3 15
+
+# input
+cp data/example.tsv "${tmpdir}/${t}.tsv"
+
+# assertion
+cp data/example.tsv "${tmpdir}/${t}.assert"
+
+# action
+cd "${tmpdir}" || exit 1
+orcli import tsv "${t}.tsv" --projectName "${t}"
+orcli export tsv "${t}" > "${t}.output"
+
+# test
+diff -u "${t}.assert" "${t}.output"

tests/info.sh

@@ -18,8 +18,8 @@ DATA
 
 # action
 cd "${tmpdir}" || exit 1
-orcli import csv "${t}.csv"
+orcli import csv "${t}.csv" --projectName "${t}"
-orcli info "${t} csv" | jq -r .columns[] > "${t}.output"
+orcli info "${t}" | jq -r .columns[] > "${t}.output"
 
 # test
 diff -u "${t}.assert" "${t}.output"

tests/list.sh

@@ -11,7 +11,7 @@ cp data/example.csv "${tmpdir}/${t}.csv"
 
 # action
 cd "${tmpdir}" || exit 1
-orcli import csv "${t}.csv"
+orcli import csv "${t}.csv" --projectName "${t}"
 orcli list > "${t}.output"
 
 # test