proper readme, prepare for release

Cargo.toml

@@ -3,9 +3,17 @@ name = "pink_accents"
 version = "0.0.1"
 authors = ["fogapod"]
 edition = "2021"
-description = "Accent system based on string pattern matching"
+description = "Replacement of patterns in string to simulate speech accents"
+repository = "https://github.com/Fogapod/pink_accents"
+homepage = "https://github.com/Fogapod/pink_accents"
 license = "AGPL-3.0"
-exclude = ["/.github", "/examples/accents", "/tests/sample_text.txt"]
+keywords = ["text"]
+categories = ["text-processing"]
+exclude = [
+    "/.github",
+    "/examples",
+    "/tests/sample_text.txt",
+]
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 

README.md

@@ -1,9 +1,103 @@
 # pink accents
 
-Accent system based on string pattern matching.
+Allows defining a set of patterns to be replaced in string. This is a glorified regex replace, a sequence of them. Primary use case is for simulating silly speech accents.
 
-Originally based on python [pink-accents](https://git.based.computer/fogapod/pink-accents) and
-primarily developed for [ssnt](https://github.com/SS-NT/ssnt/tree/main)
-game.
+Originally based on python [pink-accents](https://git.based.computer/fogapod/pink-accents) and primarily developed for [ssnt](https://github.com/SS-NT/ssnt/tree/main) game.
 
-See examples in [examples](examples/accents) folder.
+Currently unusable on it's own because you cannot construct `Accent` using internal structures but there is a plan to support programmatic definitions.
+
+## Types of replacements
+
+Accent is a sequence of rules which are applied in order.
+Each rule consists of regex pattern and a replacement. When regex match occurs the replacement is called. It then decides what to put instead (if anything).
+
+Possible replacements are:
+
+- `Noop`: Do not replace
+- `Simple`: Puts string as is
+- `Any` (recursive): Selects random replacement with equal weights
+- `Weights` (recursive): Selects replacement based on relative weights
+
+## Serialized format
+
+`deserialize` feature provides an opinionated way of defining rules, specifically designed for speech accents.
+Deserialization is primarily developed to support [ron](https://github.com/ron-rs/ron) format which has it's quirks but should work in json and maybe others.
+
+Full reference:
+
+```ron
+(
+    // on by default, tries to match input case with output after each rule
+    // for example, if you replaced "HELLO" with "bye", it would use "BYE" instead
+    normalize_case: true,
+
+    // pairs of (regex, replacement)
+    // this is same as `patterns` except that each regex is surrounded with \b to avoid copypasting.
+    // `words` are applied before `patterns`
+    words: [
+        // this is the simplest rule to replace all "windows" words (separated by regex \b)
+        // occurences with "linux", case sensitive
+        ("windows", Simple("linux")),
+        // this replaces word "OS" with one of replacements, with equal probability
+        ("os", Any([
+            Simple("Ubuntu"),
+            Simple("Arch"),
+            Simple("Gentoo"),
+        ])),
+    ],
+
+    // pairs of (regex, replacement)
+    // this is same as `words` except these are used as is, without \b
+    patterns: [
+        // inserts one of the honks. first value of `Weights` is relative weight. higher is better
+        ("$", Weights([
+            (32, Simple(" HONK!")),
+            (16, Simple(" HONK HONK!")),
+            (08, Simple(" HONK HONK HONK!")),
+            // ultra rare sigma honk - 1 / 56
+            (01, Simple(" HONK HONK HONK HONK!!!!!!!!!!!!!!!")),
+        ])),
+    ],
+
+    // accent can be used with severity (non negative value). higher severities can either extend
+    // lower level or completely replace it.
+    // default severity is 0. higher ones are defined here
+    severities: {
+        // extends previous severity (level 0, base one in this case), adding additional rules
+        // below existingones. words and patterns keep their relative order though - words are
+        // processed first
+        1: Extend(
+            (
+                words: [
+                    // even though we are extending, defining same rule will overwrite result.
+                    // relative order of rules remain the same: "windows" will remain first
+                    ("windows", Simple("windoos")),
+                ],
+
+                // extend patterns, adding 1 more rule
+                patterns: [
+                    // replacements can be nested arbitrarily
+                    ("[A-Z]", Weights([
+                        // 50% to replace capital letter with one of the Es
+                        (1, Any([
+                            Simple("E"),
+                            Simple("Ē"),
+                            Simple("Ê"),
+                            Simple("Ë"),
+                            Simple("È"),
+                            Simple("É"),
+                        ])),
+                        // 50% to do nothing, no replacement
+                        (1, Noop),
+                    ])),
+                ],
+            ),
+        ),
+
+        // replace severity 1 entirely. in this case with nothing. remove all rules on severity 2+
+        2: Replace(()),
+    },
+)
+```
+
+See more examples in [examples](examples) folder.

examples/accents/example.ron → examples/example.ron

@@ -14,7 +14,7 @@
     // this is same as `patterns` except that each regex is surrounded with \b to avoid copypasting.
     // `words` are applied before `patterns`
     words: [
-        // this is the simplest rule to replace all "windows" words (separated by regex \b) 
+        // this is the simplest rule to replace all "windows" words (separated by regex \b)
         // occurences with "linux", case sensitive
         ("windows", Simple("linux")),
         // this replaces word "OS" with one of replacements, with equal probability

src/accent.rs

@@ -647,7 +647,7 @@ mod tests {
     fn example_accents() {
         let sample_text = fs::read_to_string("tests/sample_text.txt").expect("reading sample text");
 
-        for file in fs::read_dir("examples/accents").expect("read symlinked accents folder") {
+        for file in fs::read_dir("examples").expect("read symlinked accents folder") {
             let filename = file.expect("getting file info").path();
             println!("parsing {}", filename.display());