refactor(rules): config format (#47)

Author: cmdoret

docs/tutorial.md

@@ -23,11 +23,7 @@ There are three possible ways to pseudonymize RDF triples:
 2. Pseudonymize values for specific subject-predicate combinations.
 3. Pseudonymize any value for a given predicate.
 
-By using all three ways together, we're able to get an RDF file with sensitive
-information:
-
-<details>
-    <summary><b>Click to show input</b></summary>
+By combining these, can process an RDF file with sensitive information:
 
 ```ntriples
 <http://example.org/Alice> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Person> .
@@ -40,15 +36,12 @@ information:
 <http://example.org/Bank> <http://schema.org/name> "Bank" .
 ```
 
-</details>
 
-And pseudonymize the sensitive information such as people's names, personal and
-secret information while keeping the rest as is:
+into a pseudonymized file where the sensitive information such as people's names, personal and
+secret information is hashed to protect privacy:
 
-<details>
-    <summary><b>Click to show output</b></summary>
 
-```
+```ntriples
 <http://example.org/af321bbc> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Person> .
 <http://example.org/af321bbc> <http://xmlns.com/foaf/0.1/holdsAccount> <http://example.org/bs2313bc> .
 <http://example.org/bs2313bc> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/OnlineAccount> .
@@ -59,55 +52,49 @@ secret information while keeping the rest as is:
 <http://example.org/Bank> <http://schema.org/name> "Bank" .
 ```
 
-</details>
-
 The next subsections break down each of the three pseudonymization approaches to
 better understand how they operate.
 
 ### 1. Pseudonymize the URI of nodes with `rdf:type`
 
-<details>
-    <summary><b>Click to show</b></summary>
 
 Given the following config:
 
 ```yaml
-replace_uri_of_nodes_with_type:
+subjects:
+  of_type:
   - "http://xmlns.com/foaf/0.1/Person"
 ```
 
 The goal is to pseudonymize all instaces of `rdf:type` Person. The following
 input file:
 
-```
+```ntriples
 <http://example.org/Alice> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Person> .
 ```
 
 Would become:
 
-```
+```ntriples
 <http://example.org/af321bbc> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Person> .
 ```
 
-</details>
 
 ### 2. Pseudonymize values for specific subject-predicate combinations
 
-<details>
-    <summary><b>Click to show</b></summary>
-
 Given the following config:
 
 ```yaml
-replace_values_of_subject_predicate:
-  "http://xmlns.com/foaf/0.1/Person":
+objects:
+  on_type_predicate:
+    "http://xmlns.com/foaf/0.1/Person":
     - "http://schema.org/name"
 ```
 
 The goal is to pseudonymize only the instances of names when they're associated
 to Person. The following input file:
 
-```
+```ntriples
 <http://example.org/Alice> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Person> .
 <http://example.org/Alice> <http://schema.org/name> "Alice" .
 <http://example.org/Bank> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Organization> .
@@ -116,19 +103,15 @@ to Person. The following input file:
 
 Would become:
 
-```
+```ntriples
 <http://example.org/Alice> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Person> .
 <http://example.org/Alice> <http://schema.org/name> "af321bbc" .
 <http://example.org/Bank> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Organization> .
 <http://example.org/Bank> <http://schema.org/name> "Bank" .
 ```
 
-</details>
-
 ### 3. Pseudonymize any value for a given predicate
 
-<details>
-    <summary><b>Click to show</b></summary>
 
 Given the following config:
 
@@ -140,7 +123,7 @@ replace_value_of_predicate:
 The goal is to pseudonymize any values associated to name. The following input
 file:
 
-```
+```ntriples
 <http://example.org/Alice> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Person> .
 <http://example.org/Alice> <http://schema.org/name> "Alice" .
 <http://example.org/Bank> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Organization> .
@@ -149,11 +132,9 @@ file:
 
 Would become:
 
-```
+```ntriples
 <http://example.org/Alice> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Person> .
 <http://example.org/Alice> <http://schema.org/name> "af321bbc" .
 <http://example.org/Bank> <http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://xmlns.com/foaf/0.1/Organization> .
 <http://example.org/Bank> <http://schema.org/name> "38a3dd71" .
 ```
-
-</details>

src/pass_first.rs src/index.rssrc/pass_first.rs renamed to src/index.rs

@@ -1,18 +1,18 @@
 // Define the module.
 mod crypto;
+mod index;
 mod io;
 mod log;
 mod model;
-mod pass_first;
-mod pass_second;
+mod pseudo;
 mod rdf_types;
 mod rules;
 
 // Define the imports.
 use crate::{
+    index::create_type_map,
     log::{create_logger, info},
-    pass_first::create_type_map,
-    pass_second::pseudonymize_graph,
+    pseudo::pseudonymize_graph,
 };
 
 use clap::{Args, Parser, Subcommand};
@@ -51,11 +51,6 @@ struct PseudoArgs {
     #[arg(default_value = "-")]
     input: PathBuf,
 
-    /// Invert the matching rules for the subject and the object.
-    /// Disabled by default
-    #[arg(short = 'v', long)]
-    invert_match: bool,
-
     /// The config file descriptor to use for defining RDF elements to pseudonymize.
     /// Format: yaml
     #[arg(short, long)]
@@ -103,7 +98,6 @@ fn main() {
                 &args.output,
                 &args.index,
                 &args.secret,
-                &args.invert_match,
             )
         }
     }

src/main.rs

@@ -10,35 +10,10 @@ use crate::{
     crypto::{new_pseudonymizer, Pseudonymize},
     io,
     log::Logger,
-    model::TripleMask,
     rdf_types::*,
-    rules::{
-        match_predicate_rule, match_subject_predicate_rule, match_type_rule_object,
-        match_type_rule_subject, Rules,
-    },
+    rules::{match_rules, Rules},
 };
 
-fn match_rules(
-    triple: Triple,
-    rules: &Rules,
-    type_map: &HashMap<String, String>,
-    invert_match: &bool,
-) -> TripleMask {
-    // Check each field of the triple against the rules
-    let mut mask = TripleMask::default();
-
-    mask = match_type_rule_subject(&triple.subject, mask, type_map, rules);
-    mask = match_type_rule_object(&triple.object, mask, type_map, rules);
-    mask = match_predicate_rule(&triple.predicate, mask, rules);
-    mask = match_subject_predicate_rule(&triple.subject, &triple.predicate, mask, type_map, rules);
-
-    if *invert_match {
-        mask = mask.invert();
-    }
-
-    return mask;
-}
-
 // mask and encode input triple
 // NOTE: This will need the type-map to perform masking
 fn process_triple(
@@ -47,9 +22,8 @@ fn process_triple(
     node_to_type: &HashMap<String, String>,
     out: &mut impl Write,
     hasher: &dyn Pseudonymize,
-    invert_match: &bool,
 ) {
-    let mask = match_rules(triple.clone(), rules_config, node_to_type, invert_match);
+    let mask = match_rules(&triple, rules_config, node_to_type);
 
     let r = || -> std::io::Result<()> {
         out.write_all(hasher.pseudo_triple(&triple, mask).to_string().as_bytes())?;
@@ -86,7 +60,6 @@ pub fn pseudonymize_graph(
     output: &Path,
     index: &Path,
     secret_path: &Option<PathBuf>,
-    invert_match: &bool,
 ) {
     let buf_input = io::get_reader(input);
     let buf_index = io::get_reader(index);
@@ -110,7 +83,6 @@ pub fn pseudonymize_graph(
                     &node_to_type,
                     &mut buf_output,
                     &pseudonymizer,
-                    invert_match,
                 );
                 Result::<(), TurtleError>::Ok(())
             })
@@ -139,15 +111,13 @@ mod tests {
         let output_path = dir.path().join("output.nt");
         let type_map_path = Path::new("tests/data/type_map.nt");
         let key = None;
-        let invert_match = false;
         pseudonymize_graph(
             &logger,
             &input_path,
             &config_path,
             &output_path,
             &type_map_path,
             &key,
-            &invert_match,
         );
     }
 }