Re: [PR] Make regexp_match take scalar pattern and flag [arrow-rs]

["viirya (via GitHub)" <gi...@apache.org>]

viirya commented on code in PR #5245:
URL: https://github.com/apache/arrow-rs/pull/5245#discussion_r1438954780


##########
arrow-string/src/regexp.rs:
##########
@@ -248,6 +227,186 @@ pub fn regexp_match<OffsetSize: OffsetSizeTrait>(
     Ok(Arc::new(list_builder.finish()))
 }
 
+fn get_scalar_pattern_flag<'a, OffsetSize: OffsetSizeTrait>(
+    regex_array: &'a dyn Array,
+    flag_array: Option<&'a dyn Array>,
+) -> (Option<&'a str>, Option<&'a str>) {
+    let regex = regex_array
+        .as_any()
+        .downcast_ref::<GenericStringArray<OffsetSize>>()
+        .expect("Unable to downcast to StringArray/LargeStringArray");
+    let regex = if regex.is_valid(0) {
+        Some(regex.value(0))
+    } else {
+        None
+    };
+
+    if flag_array.is_some() {
+        let flag = flag_array
+            .unwrap()
+            .as_any()
+            .downcast_ref::<GenericStringArray<OffsetSize>>()
+            .expect("Unable to downcast to StringArray/LargeStringArray");
+
+        if flag.is_valid(0) {
+            let flag = flag.value(0);
+            (regex, Some(flag))
+        } else {
+            (regex, None)
+        }
+    } else {
+        (regex, None)
+    }
+}
+
+fn regexp_scalar_match<OffsetSize: OffsetSizeTrait>(
+    array: &GenericStringArray<OffsetSize>,
+    regex: &Regex,
+) -> std::result::Result<ArrayRef, ArrowError> {
+    let builder: GenericStringBuilder<OffsetSize> = GenericStringBuilder::with_capacity(0, 0);
+    let mut list_builder = ListBuilder::new(builder);
+
+    array
+        .iter()
+        .map(|value| {
+            match value {
+                // Required for Postgres compatibility:
+                // SELECT regexp_match('foobarbequebaz', ''); = {""}
+                Some(_) if regex.as_str() == "" => {
+                    list_builder.values().append_value("");
+                    list_builder.append(true);
+                }
+                Some(value) => match regex.captures(value) {
+                    Some(caps) => {
+                        let mut iter = caps.iter();
+                        if caps.len() > 1 {
+                            iter.next();
+                        }
+                        for m in iter.flatten() {
+                            list_builder.values().append_value(m.as_str());
+                        }
+
+                        list_builder.append(true);
+                    }
+                    None => list_builder.append(false),
+                },
+                _ => list_builder.append(false),
+            }
+            Ok(())
+        })
+        .collect::<Result<Vec<()>, ArrowError>>()?;
+
+    Ok(Arc::new(list_builder.finish()))
+}
+
+/// Extract all groups matched by a regular expression for a given String array.
+///
+/// Modelled after the Postgres [regexp_match].
+///
+/// Returns a ListArray of [`GenericStringArray`] with each element containing the leftmost-first
+/// match of the corresponding index in `regex_array` to string in `array`
+///
+/// If there is no match, the list element is NULL.
+///
+/// If a match is found, and the pattern contains no capturing parenthesized subexpressions,
+/// then the list element is a single-element [`GenericStringArray`] containing the substring
+/// matching the whole pattern.
+///
+/// If a match is found, and the pattern contains capturing parenthesized subexpressions, then the
+/// list element is a [`GenericStringArray`] whose n'th element is the substring matching
+/// the n'th capturing parenthesized subexpression of the pattern.
+///
+/// The flags parameter is an optional text string containing zero or more single-letter flags
+/// that change the function's behavior.
+///
+/// [regexp_match]: https://www.postgresql.org/docs/current/functions-matching.html#FUNCTIONS-POSIX-REGEXP
+pub fn regexp_match<OffsetSize: OffsetSizeTrait>(
+    array: &GenericStringArray<OffsetSize>,

Review Comment:
   Yea



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@arrow.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org