Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fixes #16559 - Do not trim leading spaces for tab delimited #17442

Merged
merged 7 commits into from
Oct 26, 2021
Merged

Fixes #16559 - Do not trim leading spaces for tab delimited #17442

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
ec3137b
Fixes #16559 - Do not trim leading spaces for tab delimited
richmahn Oct 26, 2021
a4f0782
Adds back semicolon delimited test
richmahn Oct 26, 2021
18802c4
Fixes linting
richmahn Oct 26, 2021
ef4d82e
Adds nolint directive to test because uses strings starting with spaces
richmahn Oct 26, 2021
61585fc
Merge branch 'main' into richmahn-16559-tsv-no-trim-space
zeripath Oct 26, 2021
883ebae
Merge remote-tracking branch 'origin/main' into richmahn-16559-tsv-no…
richmahn Oct 26, 2021
2552060
Merge branch 'richmahn-16559-tsv-no-trim-space' of github.com:richmah…
richmahn Oct 26, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion modules/csv/csv.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,11 @@ var quoteRegexp = regexp.MustCompile(`["'][\s\S]+?["']`)
func CreateReader(input io.Reader, delimiter rune) *stdcsv.Reader {
rd := stdcsv.NewReader(input)
rd.Comma = delimiter
rd.TrimLeadingSpace = true
if delimiter != '\t' && delimiter != ' ' {
// TrimLeadingSpace can't be true when delimiter is a tab or a space as the value for a column might be empty,
// thus would change `\t\t` to just `\t` or ` ` (two spaces) to just ` ` (single space)
rd.TrimLeadingSpace = true
}
Comment on lines +25 to +29
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
if delimiter != '\t' && delimiter != ' ' {
// TrimLeadingSpace can't be true when delimiter is a tab or a space as the value for a column might be empty,
// thus would change `\t\t` to just `\t` or ` ` (two spaces) to just ` ` (single space)
rd.TrimLeadingSpace = true
}
// TrimLeadingSpace can't be true when delimiter is a tab or a space as the value for a column might be empty,
// thus would change `\t\t` to just `\t` or ` ` (two spaces) to just ` ` (single space)
rd.TrimLeadingSpace = delimiter != '\t' && delimiter != ' '

return rd
}

Expand Down
55 changes: 48 additions & 7 deletions modules/csv/csv_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,16 +17,57 @@ func TestCreateReader(t *testing.T) {
assert.Equal(t, ',', rd.Comma)
}

//nolint
func TestCreateReaderAndGuessDelimiter(t *testing.T) {
input := "a;b;c\n1;2;3\n4;5;6"
var csvToRowsMap = map[string][][]string{
`a;b;c
1;2;3
4;5;6`: {{"a", "b", "c"}, {"1", "2", "3"}, {"4", "5", "6"}},
`col1 col2 col3
a b c
e f
g h i
j l
m n
p q r
u
v w x
y
`: {{"col1", "col2", "col3"},
{"a", "b", "c"},
{"", "e", "f"},
{"g", "h", "i"},
{"j", "", "l"},
{"m", "n", ""},
{"p", "q", "r"},
{"", "", "u"},
{"v", "w", "x"},
{"y", "", ""},
{"", "", ""}},
` col1,col2,col3
a, b, c
d,e,f
,h, i
j, ,
, , `: {{"col1", "col2", "col3"},
{"a", "b", "c"},
{"d", "e", "f"},
{"", "h", "i"},
{"j", "", ""},
{"", "", ""}},
}

rd, err := CreateReaderAndGuessDelimiter(strings.NewReader(input))
assert.NoError(t, err)
assert.Equal(t, ';', rd.Comma)
for csv, expectedRows := range csvToRowsMap {
rd, err := CreateReaderAndGuessDelimiter(strings.NewReader(csv))
assert.NoError(t, err)
rows, err := rd.ReadAll()
assert.NoError(t, err)
assert.EqualValues(t, rows, expectedRows)
}
}

func TestGuessDelimiter(t *testing.T) {
var kases = map[string]rune{
var csvToDelimiterMap = map[string]rune{
"a": ',',
"1,2": ',',
"1;2": ';',
Expand All @@ -37,7 +78,7 @@ func TestGuessDelimiter(t *testing.T) {
"<br/>": ',',
}

for k, v := range kases {
assert.EqualValues(t, guessDelimiter([]byte(k)), v)
for csv, expectedDelimiter := range csvToDelimiterMap {
assert.EqualValues(t, guessDelimiter([]byte(csv)), expectedDelimiter)
}
}