Merge branch 'main' into feature/output_json

Cargo.toml

@@ -14,6 +14,7 @@ csv = "1.3.0"
 env_logger = "0.10"
 fastrand = "2.0.1"
 fastrand-contrib = "0.1.0"
+linked-hash-map = "0.5.6"
 log = "0.4"
 once_cell = "1.8"
 parquet = "50.0.0"

docs/columns/providers/constant.md

@@ -0,0 +1,36 @@
+Constant provider
+-------
+
+### string
+#### unique value
+```yaml
+ - name: constant_as_string
+   provider: Constant.string
+   data: trout
+```
+
+#### list of values
+```yaml
+ - name: list_of_constants_as_string
+   provider: Constant.string
+   data: [trout, salmon, carp]
+```
+
+#### list of weighted values
+```yaml
+ - name: list_of_weighted_constants_as_string
+   provider: Constant.string
+   data: 
+     - value: trout
+     - value: salmon
+       weight: 8
+     - value: carp
+```
+
+Data value can be unique value, a list of values or a dictionnary.  
+Integer, float or string can be specify into the configuration but the result will be stored as a string.
+If a unique value is specified, all lines will have this value.  
+If a list of values is specified, value will randomly assigned for each line.  
+If a weighted list of values is specified, value will weighted randomly assigned for each line: for example is useful to generate data skewing.  
+ 
+[Options](../options.md) are also possible.

src/providers/constant/builder.rs

@@ -0,0 +1,48 @@
+use yaml_rust::Yaml;
+
+use crate::{errors::FakeLakeError, providers::provider::Provider};
+
+use super::string;
+
+pub fn get_corresponding_provider(
+    mut provider_split: std::str::Split<'_, char>,
+    column: &Yaml,
+) -> Result<Box<dyn Provider>, FakeLakeError> {
+    match provider_split.next() {
+        Some("string") => Ok(string::new_from_yaml(column)),
+        _ => Err(FakeLakeError::BadYAMLFormat("".to_string())),
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::get_corresponding_provider;
+
+    use yaml_rust::YamlLoader;
+
+    #[test]
+    fn given_string_should_return_provider() {
+        let provider_name = "string";
+        let yaml_str = format!("name: is_suscribed{}provider: {}", '\n', provider_name);
+        let column = &YamlLoader::load_from_str(yaml_str.as_str()).unwrap()[0];
+
+        let provider_split = provider_name.split('.');
+        match get_corresponding_provider(provider_split, column) {
+            Ok(_) => (),
+            _ => panic!(),
+        }
+    }
+
+    #[test]
+    fn given_wrong_provider_should_return_error() {
+        let provider_name = "not_a_provider";
+        let yaml_str = format!("name: email{}provider: {}", '\n', provider_name);
+        let column = &YamlLoader::load_from_str(yaml_str.as_str()).unwrap()[0];
+
+        let provider_split = provider_name.split('.');
+        match get_corresponding_provider(provider_split, column) {
+            Err(_) => (),
+            _ => panic!(),
+        }
+    }
+}

src/providers/constant/mod.rs

@@ -0,0 +1,3 @@
+pub mod builder;
+
+pub mod string;