feat: remove XML input format. (#15540)

* feat: remove XML input format.

* fix

Author: youngsofun

Cargo.lock

@@ -85,7 +85,6 @@ impl FileFormatParams {
             StageFileFormatType::Json => {
                 Ok(FileFormatParams::Json(JsonFileFormatParams::default()))
             }
-            StageFileFormatType::Xml => Ok(FileFormatParams::Xml(XmlFileFormatParams::default())),
             _ => Err(ErrorCode::IllegalFileFormat(format!(
                 "Unsupported file format type: {:?}",
                 format_type
@@ -271,9 +270,6 @@ impl FileFormatParams {
                 check_option!(p, escape)?;
                 check_option!(p, nan_display)?;
             }
-            FileFormatParams::Xml(p) => {
-                check_option!(p, row_tag)?;
-            }
             _ => {}
         }
         Ok(())

src/meta/app/src/principal/file_format.rs

@@ -194,10 +194,10 @@ impl FromStr for StageFileFormatType {
             "XML" => Ok(StageFileFormatType::Xml),
             "JSON" => Ok(StageFileFormatType::Json),
             "ORC" | "AVRO" => Err(format!(
-                "File format type '{s}' not implemented yet', must be one of ( CSV | TSV | NDJSON | PARQUET | XML)"
+                "File format type '{s}' not implemented yet', must be one of ( CSV | TSV | NDJSON | PARQUET)"
             )),
             _ => Err(format!(
-                "Unknown file format type '{s}', must be one of ( CSV | TSV | NDJSON | PARQUET | XML)"
+                "Unknown file format type '{s}', must be one of ( CSV | TSV | NDJSON | PARQUET)"
             )),
         }
     }

src/meta/app/src/principal/user_stage.rs

@@ -77,7 +77,7 @@ pub fn connection_options(i: Input) -> IResult<BTreeMap<String, String>> {
 pub fn format_options(i: Input) -> IResult<FileFormatOptions> {
     let option_type = map(
         rule! {
-            TYPE ~ "=" ~ ( TSV | CSV | NDJSON | PARQUET | JSON | XML )
+            TYPE ~ "=" ~ ( TSV | CSV | NDJSON | PARQUET | JSON )
         },
         |(_, _, v)| {
             (

src/query/ast/src/parser/stage.rs

@@ -40,7 +40,6 @@ use databend_common_io::constants::FALSE_BYTES_NUM;
 use databend_common_io::constants::INF_BYTES_LOWER;
 use databend_common_io::constants::NAN_BYTES_LOWER;
 use databend_common_io::constants::NULL_BYTES_ESCAPE;
-use databend_common_io::constants::NULL_BYTES_LOWER;
 use databend_common_io::constants::TRUE_BYTES_LOWER;
 use databend_common_io::constants::TRUE_BYTES_NUM;
 use databend_common_io::cursor_ext::collect_number;
@@ -52,7 +51,6 @@ use databend_common_io::parse_bitmap;
 use databend_common_io::parse_to_ewkb;
 use databend_common_meta_app::principal::CsvFileFormatParams;
 use databend_common_meta_app::principal::TsvFileFormatParams;
-use databend_common_meta_app::principal::XmlFileFormatParams;
 use jsonb::parse_value;
 use lexical_core::FromLexical;
 use num_traits::NumCast;
@@ -112,23 +110,6 @@ impl SeparatedTextDecoder {
         }
     }
 
-    pub fn create_xml(_params: &XmlFileFormatParams, options_ext: &FileFormatOptionsExt) -> Self {
-        SeparatedTextDecoder {
-            common_settings: InputCommonSettings {
-                null_if: vec![NULL_BYTES_LOWER.as_bytes().to_vec()],
-                true_bytes: TRUE_BYTES_LOWER.as_bytes().to_vec(),
-                false_bytes: FALSE_BYTES_LOWER.as_bytes().to_vec(),
-                nan_bytes: NAN_BYTES_LOWER.as_bytes().to_vec(),
-                inf_bytes: INF_BYTES_LOWER.as_bytes().to_vec(),
-                timezone: options_ext.timezone,
-                disable_variant_check: options_ext.disable_variant_check,
-                binary_format: Default::default(),
-                is_rounding_mode: options_ext.is_rounding_mode,
-            },
-            nested_decoder: NestedValues::create(options_ext),
-        }
-    }
-
     fn common_settings(&self) -> &InputCommonSettings {
         &self.common_settings
     }

src/query/formats/src/field_decoder/separated_text.rs

@@ -11,9 +11,6 @@ edition = { workspace = true }
 doctest = false
 test = true
 
-[package.metadata.cargo-machete]
-ignored = ["xml-rs"]
-
 [dependencies]
 async-backtrace = { workspace = true }
 async-channel = "1.7.1"
@@ -45,4 +42,3 @@ serde = { workspace = true }
 serde_json = { workspace = true }
 
 typetag = { workspace = true }
-xml-rs = "0.8.14"