Add in support for setting delim when parsing JSON through java #16867
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Robert (Bobby) Evans <[email protected]>
revans2
added
3 - Ready for Review
abellina
approved these changes
Sep 20, 2024
ttnghia
reviewed
Sep 20, 2024
| @@ -38,6 +38,7 @@ public final class JSONOptions extends ColumnFilterOptions { | |||
| private final boolean allowLeadingZeros; | |||
| private final boolean allowNonNumericNumbers; | |||
| private final boolean allowUnquotedControlChars; | |||
| private final byte delim; | |||
There was a problem hiding this comment.
Let's use the full name delimiter.
Suggested change
| private final byte delim; | |
| private final byte delimiter; |
ttnghia
reviewed
Sep 21, 2024
Comment on lines
56
to
60
| delim = builder.delim; | ||
| } | ||
|
|
||
| public byte getDelim() { | ||
| return delim; |
There was a problem hiding this comment.
Suggested change
| delim = builder.delim; | |
| } | |
| public byte getDelim() { | |
| return delim; | |
| delim = builder.delim; | |
| } | |
| public byte getDelimiter() { | |
| return delimiter; |
ttnghia
reviewed
Sep 21, 2024
Comment on lines
132
to
140
| private byte delim = '\n'; | ||
|
|
||
| public Builder withDelim(char delimiter) { | ||
| if (delimiter > Byte.MAX_VALUE) { | ||
| throw new IllegalArgumentException("Only basic ASCII values are supported " + delimiter); | ||
| } | ||
| delim = (byte)delimiter; | ||
| return this; | ||
| } |
There was a problem hiding this comment.
Suggested change
| private byte delim = '\n'; | |
| public Builder withDelim(char delimiter) { | |
| if (delimiter > Byte.MAX_VALUE) { | |
| throw new IllegalArgumentException("Only basic ASCII values are supported " + delimiter); | |
| } | |
| delim = (byte)delimiter; | |
| return this; | |
| } | |
| private byte delimiter = '\n'; | |
| public Builder withDelimiter(char delimiter) { | |
| if (delimiter > Byte.MAX_VALUE) { | |
| throw new IllegalArgumentException("Only basic ASCII values are supported " + delimiter); | |
| } | |
| this.delimiter = (byte)delimiter; | |
| return this; | |
| } |
ttnghia
reviewed
Sep 21, 2024
| @@ -258,7 +258,8 @@ private static native long readJSON(int[] numChildren, String[] columnNames, | |||
| boolean strictValidation, | |||
| boolean allowLeadingZeros, | |||
| boolean allowNonNumericNumbers, | |||
| boolean allowUnquotedControl) throws CudfException; | |||
| boolean allowUnquotedControl, | |||
| byte delim) throws CudfException; | |||
There was a problem hiding this comment.
Suggested change
| byte delim) throws CudfException; | |
| byte delimiter) throws CudfException; |
ttnghia
reviewed
Sep 21, 2024
| @@ -272,6 +273,7 @@ private static native long readJSONFromDataSource(int[] numChildren, String[] co | |||
| boolean allowLeadingZeros, | |||
| boolean allowNonNumericNumbers, | |||
| boolean allowUnquotedControl, | |||
| byte delim, | |||
There was a problem hiding this comment.
Suggested change
| byte delim, | |
| byte delimiter, |
ttnghia
reviewed
Sep 21, 2024
| @@ -284,6 +286,7 @@ private static native long readAndInferJSONFromDataSource(boolean dayFirst, bool | |||
| boolean allowLeadingZeros, | |||
| boolean allowNonNumericNumbers, | |||
| boolean allowUnquotedControl, | |||
| byte delim, | |||
There was a problem hiding this comment.
Suggested change
| byte delim, | |
| byte delimiter, |
ttnghia
reviewed
Sep 21, 2024
| @@ -297,7 +300,8 @@ private static native long readAndInferJSON(long address, long length, | |||
| boolean strictValidation, | |||
| boolean allowLeadingZeros, | |||
| boolean allowNonNumericNumbers, | |||
| boolean allowUnquotedControl) throws CudfException; | |||
| boolean allowUnquotedControl, | |||
| byte delim) throws CudfException; | |||
There was a problem hiding this comment.
Suggested change
| byte delim) throws CudfException; | |
| byte delimiter) throws CudfException; |
ttnghia
reviewed
Sep 21, 2024
| @@ -1321,7 +1325,8 @@ public static Table readJSON(Schema schema, JSONOptions opts, File path) { | |||
| opts.strictValidation(), | |||
| opts.leadingZerosAllowed(), | |||
| opts.nonNumericNumbersAllowed(), | |||
| opts.unquotedControlChars()))) { | |||
| opts.unquotedControlChars(), | |||
| opts.getDelim()))) { | |||
There was a problem hiding this comment.
Suggested change
| opts.getDelim()))) { | |
| opts.getDelimiter()))) { |
ttnghia
reviewed
Sep 21, 2024
| @@ -1404,7 +1409,8 @@ public static TableWithMeta readJSON(JSONOptions opts, HostMemoryBuffer buffer, | |||
| opts.strictValidation(), | |||
| opts.leadingZerosAllowed(), | |||
| opts.nonNumericNumbersAllowed(), | |||
| opts.unquotedControlChars())); | |||
| opts.unquotedControlChars(), | |||
| opts.getDelim())); | |||
There was a problem hiding this comment.
Suggested change
| opts.getDelim())); | |
| opts.getDelimiter())); |
ttnghia
reviewed
Sep 21, 2024
| @@ -1426,6 +1432,7 @@ public static TableWithMeta readAndInferJSON(JSONOptions opts, DataSource ds) { | |||
| opts.leadingZerosAllowed(), | |||
| opts.nonNumericNumbersAllowed(), | |||
| opts.unquotedControlChars(), | |||
| opts.getDelim(), | |||
There was a problem hiding this comment.
Suggested change
| opts.getDelim(), | |
| opts.getDelimiter(), |
ttnghia
reviewed
Sep 21, 2024
| @@ -1479,7 +1486,8 @@ public static Table readJSON(Schema schema, JSONOptions opts, HostMemoryBuffer b | |||
| opts.strictValidation(), | |||
| opts.leadingZerosAllowed(), | |||
| opts.nonNumericNumbersAllowed(), | |||
| opts.unquotedControlChars()))) { | |||
| opts.unquotedControlChars(), | |||
| opts.getDelim()))) { | |||
There was a problem hiding this comment.
Suggested change
| opts.getDelim()))) { | |
| opts.getDelimiter()))) { |
ttnghia
reviewed
Sep 21, 2024
| @@ -1518,6 +1526,7 @@ public static Table readJSON(Schema schema, JSONOptions opts, DataSource ds, int | |||
| opts.leadingZerosAllowed(), | |||
| opts.nonNumericNumbersAllowed(), | |||
| opts.unquotedControlChars(), | |||
| opts.getDelim(), | |||
There was a problem hiding this comment.
Suggested change
| opts.getDelim(), | |
| opts.getDelimiter(), |
ttnghia
reviewed
Sep 21, 2024
| Schema schema = Schema.builder().addColumn(DType.STRING, "a").build(); | ||
| JSONOptions opts = JSONOptions.builder() | ||
| .withLines(true) | ||
| .withDelim('\0') |
There was a problem hiding this comment.
Suggested change
| .withDelim('\0') | |
| .withDelimiter('\0') |
ttnghia
approved these changes
Sep 23, 2024
|
/merge |
revans2
added a commit
to revans2/cudf
that referenced
this pull request
Sep 23, 2024
…dsai#16867) This just adds in JNI APIs to allow for changing the delimiter when parsing JSON. Authors: - Robert (Bobby) Evans (https://github.com/revans2) Approvers: - Alessandro Bellina (https://github.com/abellina) - Nghia Truong (https://github.com/ttnghia) URL: rapidsai#16867
3 tasks
rapids-bot bot
pushed a commit
that referenced
this pull request
Sep 24, 2024
…) (#16880) This is a back-port of #16867 to 24.10. Authors: - Robert (Bobby) Evans (https://github.com/revans2) Approvers: - Alessandro Bellina (https://github.com/abellina) URL: #16880
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This just adds in JNI APIs to allow for changing the delimiter when parsing JSON.
Checklist