Allow $ and @ characters in field names. (#4413)

* Allow $ and @ characters in field names.

* Add test and update docs.

* Fix typo.

docs/configuration/index-config.md

@@ -491,12 +491,13 @@ src.port:53 AND query_params.ctk:e42bb897d
 ### Field name validation rules
 
 Currently Quickwit only accepts field name that matches the following regular expression:
-`[a-zA-Z][_\.\-a-zA-Z0-9]*$`
+`^[@$_\-a-zA-Z][@$_\.\-a-zA-Z0-9]{0,254}$`
 
 In plain language:
 - it needs to have at least one character.
-- it should only contain latin letter `[a-zA-Z]` digits `[0-9]` or (`.`, `-`, `_`).
-- the first character needs to be a letter.
+- it can only contain uppercase and lowercase ASCII letters `[a-zA-Z]`, digits `[0-9]`, `.`, hyphens `-`, underscores `_`, at `@` and dollar `$` signs.
+- it must not start with a dot or a digit.
+- it must be different from Quickwit's reserved field mapping names `_source`, `_dynamic`, `_field_presence`.
 
 :::caution
 For field names containing the `.` character, you will need to escape it when referencing them. Otherwise the `.` character will be interpreted as a JSON object property access. Because of this, it is recommended to avoid using field names containing the `.` character.

docs/configuration/storage-config.md

@@ -146,3 +146,5 @@ storage:
     flavor: minio
     endpoint: http://127.0.0.1:9000
 ```
+
+Note: `default_index_root_uri` or index URIs do not include the endpoint, you should set it as a typical S3 path such as `s3://indexes`.

quickwit/quickwit-doc-mapper/src/default_doc_mapper/mod.rs

@@ -46,17 +46,17 @@ pub(crate) use self::tokenizer_entry::{
 use crate::QW_RESERVED_FIELD_NAMES;
 
 /// Regular expression validating a field mapping name.
-pub const FIELD_MAPPING_NAME_PATTERN: &str = r"^[_\-a-zA-Z][_\.\-a-zA-Z0-9]{0,254}$";
+pub const FIELD_MAPPING_NAME_PATTERN: &str = r"^[@$_\-a-zA-Z][@$_\.\-a-zA-Z0-9]{0,254}$";
 
 /// Validates a field mapping name.
-/// Returns `Ok(())` if the name can be used for a field mapping. Does not check for reserved field
-/// mapping names such as `_source`.
+/// Returns `Ok(())` if the name can be used for a field mapping.
 ///
 /// A field mapping name:
-/// - may only contain uppercase and lowercase ASCII letters `[a-zA-Z]`, digits `[0-9]`, hyphens
-///   `-`, and underscores `_`;
+/// - can only contain uppercase and lowercase ASCII letters `[a-zA-Z]`, digits `[0-9]`, `.`,
+///   hyphens `-`, underscores `_`, at `@` and dollar `$` signs;
 /// - must not start with a dot or a digit;
-/// - must be different from Quickwit's reserved field mapping names `_source`, `_dynamic`;
+/// - must be different from Quickwit's reserved field mapping names `_source`, `_dynamic`,
+///   `_field_presence`;
 /// - must not be longer than 255 characters.
 pub fn validate_field_mapping_name(field_mapping_name: &str) -> anyhow::Result<()> {
     static FIELD_MAPPING_NAME_PTN: Lazy<Regex> =
@@ -146,6 +146,7 @@ mod tests {
         assert!(validate_field_mapping_name("my-field").is_ok());
         assert!(validate_field_mapping_name("my.field").is_ok());
         assert!(validate_field_mapping_name("my_field").is_ok());
+        assert!(validate_field_mapping_name("$my_field@").is_ok());
         assert!(validate_field_mapping_name(&"a".repeat(255)).is_ok());
     }
 }