Skip to content

Add basic TSV support. #18

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

Merged
guymers merged 1 commit into from
Mar 23, 2026
Merged

Add basic TSV support. #18

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
89 changes: 66 additions & 23 deletions modules/core/src/main/scala/ceesvee/CsvParser.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ object CsvParser {
def maximumLineLength: Int
def skipBlankRows: Boolean
def trim: Options.Trim
def delimiter: Options.Delimiter
}
object Options {

Expand All @@ -20,27 +21,37 @@ object CsvParser {
maximumLineLength = 10_000,
skipBlankRows = false,
trim = Trim.True,
delimiter = Options.Delimiter.Comma,
)

case class Impl(
commentPrefix: Option[String],
maximumLineLength: Int,
skipBlankRows: Boolean,
trim: Trim,
delimiter: Options.Delimiter,
) extends Options

def apply(
commentPrefix: Option[String],
maximumLineLength: Int,
skipBlankRows: Boolean,
trim: Trim,
delimiter: Options.Delimiter,
): Impl = Impl(
commentPrefix = commentPrefix,
maximumLineLength = maximumLineLength,
skipBlankRows = skipBlankRows,
trim = trim,
delimiter = delimiter,
)

sealed abstract class Delimiter extends Serializable with Product
object Delimiter {
case object Comma extends Delimiter
case object Tab extends Delimiter
}

sealed abstract class Trim {
def strip(str: String): String
}
Expand Down Expand Up @@ -294,32 +305,64 @@ object CsvParser {
var insideQuote = false

while (i < line.length) {
(line(i): @switch) match {

case ',' =>
if (!insideQuote) {
{
slices.addOne(Slice(sliceStart, i))
fields addOne trimString(options, Slice.slice(slices, line))
}
i += 1
sliceStart = i
} else {
i += 1
}
options.delimiter match {
case Options.Delimiter.Comma =>
(line(i): @switch) match {

case ',' =>
if (!insideQuote) {
{
slices.addOne(Slice(sliceStart, i))
fields addOne trimString(options, Slice.slice(slices, line))
}
i += 1
sliceStart = i
} else {
i += 1
}

case '"' =>
if (insideQuote && (i + 1) < line.length && line(i + 1) == '"') { // escaped quote
slices.addOne(Slice(sliceStart, i))
sliceStart = i + 1
i += 2
} else {
i += 1
insideQuote = !insideQuote
}

case '"' =>
if (insideQuote && (i + 1) < line.length && line(i + 1) == '"') { // escaped quote
slices.addOne(Slice(sliceStart, i))
sliceStart = i + 1
i += 2
} else {
i += 1
insideQuote = !insideQuote
case _ =>
i += 1
}

case _ =>
i += 1
case Options.Delimiter.Tab =>
(line(i): @switch) match {

case '\t' =>
if (!insideQuote) {
{
slices.addOne(Slice(sliceStart, i))
fields addOne trimString(options, Slice.slice(slices, line))
}
i += 1
sliceStart = i
} else {
i += 1
}

case '"' =>
if (insideQuote && (i + 1) < line.length && line(i + 1) == '"') { // escaped quote
slices.addOne(Slice(sliceStart, i))
sliceStart = i + 1
i += 2
} else {
i += 1
insideQuote = !insideQuote
}

case _ =>
i += 1
}
}
}

Expand Down
4 changes: 4 additions & 0 deletions modules/core/src/main/scala/ceesvee/CsvReader.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,25 +11,29 @@ object CsvReader {
maximumLineLength = CsvParser.Options.Defaults.maximumLineLength,
skipBlankRows = CsvParser.Options.Defaults.skipBlankRows,
trim = CsvParser.Options.Defaults.trim,
delimiter = CsvParser.Options.Defaults.delimiter,
)

case class Impl(
commentPrefix: Option[String],
maximumLineLength: Int,
skipBlankRows: Boolean,
trim: CsvParser.Options.Trim,
delimiter: CsvParser.Options.Delimiter,
) extends Options

def apply(
commentPrefix: Option[String],
maximumLineLength: Int,
skipBlankRows: Boolean,
trim: CsvParser.Options.Trim,
delimiter: CsvParser.Options.Delimiter,
): Impl = Impl(
commentPrefix = commentPrefix,
maximumLineLength = maximumLineLength,
skipBlankRows = skipBlankRows,
trim = trim,
delimiter = delimiter,
)
}

Expand Down
12 changes: 12 additions & 0 deletions modules/core/src/test/scala/ceesvee/CsvParserSpec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,6 +104,18 @@ object CsvParserSpec extends ZIOSpecDefault with CsvParserParserSuite {
assertTrue(parseLine[List](line, Options.Defaults) == List("a", """b"c""", "d", "e\"f"))
},
),
suite("delimiter")(
test("comma") {
val line = "abc,123,data,,"
val result = parseLine[List](line, Options.Defaults.copy(delimiter = Options.Delimiter.Comma))
assertTrue(result == List("abc", "123", "data", "", ""))
},
test("tab") {
val line = "abc\t123\tdata\t\t"
val result = parseLine[List](line, Options.Defaults.copy(delimiter = Options.Delimiter.Tab))
assertTrue(result == List("abc", "123", "data", "", ""))
},
),
suite("trim")({
val line = """abc, def,ghi , jkl , " mno ", """

Expand Down