data_redactor 0.5.0 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cb5ea859ac53fad02d55edfe902ed084c2e344fdae54261ea96ea4cf84fb97ac
-  data.tar.gz: b1989344c14e784949e1130478305c4d01f1f3771b44ba4f41eb2f2ca42f6d4f
+  metadata.gz: 0c2837740c12c4424fe8837a023c6043badc61c94c99a4b53a826e57f60c362f
+  data.tar.gz: fe57411af8c23f54a462a2c71d76e8e3306adb35958001a3918e817e5bceeabc
 SHA512:
-  metadata.gz: 39ef5f9ca77539d7a1c7a6cb3c430dbd4ef7f068b67b57dbe72d8df051d36496193388440930cc5cce8e309f6760313e52b5073d3d342157841c4026210b8772
-  data.tar.gz: a40435e0034cd18d28679fa384de8ae6f9e4b3dcbdc2d5e0d14e85b85add720f4a13a9b2919ea0782fdc2a3b42c31a5c5c1515c6671e4462e74e99ccef89b273
+  metadata.gz: d882f103607569f259bd8bba0cb10a34c1967564bbe81909c6ba877ccecd020b53efc8df350ab08b19169239b4be276a5bb28c54d8559a17914d10044d2aa4d3
+  data.tar.gz: b567563554f6f8549c9207b43596a3aba7ef33bb44a6efab4df02a8e3de851c06caf2afe253a7b0f01ac1d37b4808e4c99a5f4b421d395169b7525eabc26ad3f

data/CHANGELOG.md

@@ -7,6 +7,24 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.6.0] - 2026-05-08
+
+### Added
+- **Per-pattern allow / deny via `only:` / `except:`.** Both kwargs now accept a mix of Symbols (tags) and Strings (pattern names from `DataRedactor.pattern_names`). They can be combined: `only: :contact, except: ["email"]` redacts every contact pattern except email. Mixed-list shapes like `only: [:credentials, "iban_de"]` also work. Precedence: `except:` always wins when the two overlap.
+- `DataRedactor.pattern_names` — array of every known pattern name (built-ins + currently registered custom).
+- `DataRedactor::BUILTIN_PATTERN_NAMES` and `DataRedactor::BUILTIN_PATTERN_TAG_BITS` constants (frozen) exposing the compiled-in pattern roster.
+- `DataRedactor::UnknownPatternError` raised when a String passed to `only:`/`except:` does not match any known pattern.
+- YARD docs deploy job in `.github/workflows/ci.yml` publishes `bundle exec yard doc` output to GitHub Pages on every push to `main`.
+
+### Changed
+- **C entry-point signatures.** `_redact(text, ph_mode, ph_str, enable_bits)` and `_scan(text, enable_bits)` now take a per-pattern enable bit array (built by the Ruby wrapper from `only:`/`except:`) instead of a tag bitmask. The public `DataRedactor.redact` / `.scan` API is fully backward compatible — only the underscore-prefixed C boundary changed. Single-pass: filtering happens in C, no second pass through `_scan`.
+- `only:` and `except:` may now be combined (previously raised `ArgumentError` if both were passed).
+- **Internal: C extension split into focused modules.** `ext/data_redactor/data_redactor.c` was a single ~1000-line file; it is now a 60-line entry point plus `patterns.{c,h}`, `placeholder.{c,h}`, `redact.{c,h}`, `scan.{c,h}`, `custom_patterns.{c,h}`, and `tags.h`. `extconf.rb` now globs every `.c` in the extension directory via `$srcs`, so adding a new module needs no Makefile edits.
+- **YARD inline docs** — every public method on `DataRedactor` now has `@param`/`@return`/`@raise` annotations (100% coverage); `.yardopts` configures markdown rendering with the README as the front page.
+
+### Documentation
+- README: gem version / CI / license badges; new "Thread safety" section clarifying that `redact`/`scan` are thread-safe but `add_pattern`/`remove_pattern`/`clear_custom_patterns!` are not (register custom patterns once at boot).
+
 ## [0.5.0] - 2026-05-02
 
 ### Added
@@ -62,6 +80,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - `DataRedactor.redact(text)` module function returning the input with every match replaced by `[REDACTED]`.
 - RSpec suite with one example per pattern.
 
-[Unreleased]: https://github.com/danielefrisanco/data_redactor/compare/v0.2.0...HEAD
+[Unreleased]: https://github.com/danielefrisanco/data_redactor/compare/v0.6.0...HEAD
+[0.6.0]: https://github.com/danielefrisanco/data_redactor/compare/v0.5.0...v0.6.0
 [0.2.0]: https://github.com/danielefrisanco/data_redactor/compare/v0.1.0...v0.2.0
 [0.1.0]: https://github.com/danielefrisanco/data_redactor/releases/tag/v0.1.0

data/ext/data_redactor/custom_patterns.c

@@ -0,0 +1,123 @@
+#include "custom_patterns.h"
+#include "redact.h" /* wrap_boundary */
+#include <string.h>
+#include <stdlib.h>
+
+custom_pattern_t *custom_patterns = NULL;
+int custom_count = 0;
+int custom_cap   = 0;
+
+static int find_custom_by_name(const char *name) {
+    for (int i = 0; i < custom_count; i++) {
+        if (strcmp(custom_patterns[i].name, name) == 0) return i;
+    }
+    return -1;
+}
+
+static void free_custom_at(int idx) {
+    free(custom_patterns[idx].name);
+    free(custom_patterns[idx].source);
+    regfree(&custom_patterns[idx].compiled);
+}
+
+VALUE rb_add_pattern(VALUE self, VALUE rb_name, VALUE rb_source,
+                     VALUE rb_tag_bit, VALUE rb_boundary) {
+    Check_Type(rb_name,   T_STRING);
+    Check_Type(rb_source, T_STRING);
+
+    const char *name    = StringValueCStr(rb_name);
+    const char *source  = StringValueCStr(rb_source);
+    int tag_bit         = NUM2INT(rb_tag_bit);
+    int boundary        = NUM2INT(rb_boundary);
+
+    char *pat_to_compile;
+    char *wrapped = NULL;
+    if (boundary) {
+        wrapped = wrap_boundary(source);
+        if (!wrapped) rb_raise(rb_eNoMemError, "wrap_boundary allocation failed");
+        pat_to_compile = wrapped;
+    } else {
+        pat_to_compile = (char *)source;
+    }
+
+    regex_t compiled;
+    int ret = regcomp(&compiled, pat_to_compile, REG_EXTENDED);
+    free(wrapped);
+
+    if (ret != 0) {
+        char errbuf[256];
+        regerror(ret, &compiled, errbuf, sizeof(errbuf));
+        regfree(&compiled);
+        VALUE eClass = rb_const_get(rb_define_module("DataRedactor"),
+                                    rb_intern("InvalidPatternError"));
+        rb_raise(eClass, "%s", errbuf);
+    }
+
+    int idx = find_custom_by_name(name);
+    if (idx >= 0) {
+        free_custom_at(idx);
+    } else {
+        if (custom_count >= custom_cap) {
+            int new_cap = custom_cap == 0 ? 8 : custom_cap * 2;
+            custom_pattern_t *tmp = (custom_pattern_t *)realloc(
+                custom_patterns, sizeof(custom_pattern_t) * new_cap);
+            if (!tmp) {
+                regfree(&compiled);
+                rb_raise(rb_eNoMemError, "custom_patterns realloc failed");
+            }
+            custom_patterns = tmp;
+            custom_cap = new_cap;
+        }
+        idx = custom_count++;
+    }
+
+    custom_patterns[idx].name     = strdup(name);
+    custom_patterns[idx].source   = strdup(source);
+    custom_patterns[idx].compiled = compiled;
+    custom_patterns[idx].tag      = tag_bit;
+    custom_patterns[idx].boundary = boundary;
+
+    if (!custom_patterns[idx].name || !custom_patterns[idx].source) {
+        rb_raise(rb_eNoMemError, "strdup failed");
+    }
+
+    return Qnil;
+}
+
+VALUE rb_remove_pattern(VALUE self, VALUE rb_name) {
+    Check_Type(rb_name, T_STRING);
+    const char *name = StringValueCStr(rb_name);
+
+    int idx = find_custom_by_name(name);
+    if (idx < 0) return Qfalse;
+
+    free_custom_at(idx);
+
+    for (int i = idx; i < custom_count - 1; i++) {
+        custom_patterns[i] = custom_patterns[i + 1];
+    }
+    custom_count--;
+
+    return Qtrue;
+}
+
+VALUE rb_clear_custom_patterns(VALUE self) {
+    for (int i = 0; i < custom_count; i++) {
+        free_custom_at(i);
+    }
+    custom_count = 0;
+    return Qnil;
+}
+
+VALUE rb_custom_patterns(VALUE self) {
+    VALUE arr = rb_ary_new_capa(custom_count);
+    for (int i = 0; i < custom_count; i++) {
+        VALUE h = rb_hash_new();
+        rb_hash_aset(h, ID2SYM(rb_intern("name")),     rb_str_new_cstr(custom_patterns[i].name));
+        rb_hash_aset(h, ID2SYM(rb_intern("source")),   rb_str_new_cstr(custom_patterns[i].source));
+        rb_hash_aset(h, ID2SYM(rb_intern("tag_bit")),  INT2NUM(custom_patterns[i].tag));
+        rb_hash_aset(h, ID2SYM(rb_intern("boundary")), custom_patterns[i].boundary ? Qtrue : Qfalse);
+        rb_ary_push(arr, h);
+    }
+    return arr;
+}

data/ext/data_redactor/custom_patterns.h

@@ -0,0 +1,25 @@
+#ifndef DATA_REDACTOR_CUSTOM_PATTERNS_H
+#define DATA_REDACTOR_CUSTOM_PATTERNS_H
+
+#include <ruby.h>
+#include <regex.h>
+
+typedef struct {
+    char    *name;
+    char    *source;   /* original POSIX ERE string, for introspection */
+    regex_t  compiled;
+    int      tag;      /* TAG_* bit */
+    int      boundary; /* 1 if compiled with boundary wrapper */
+} custom_pattern_t;
+
+extern custom_pattern_t *custom_patterns;
+extern int custom_count;
+extern int custom_cap;
+
+VALUE rb_add_pattern(VALUE self, VALUE rb_name, VALUE rb_source,
+                     VALUE rb_tag_bit, VALUE rb_boundary);
+VALUE rb_remove_pattern(VALUE self, VALUE rb_name);
+VALUE rb_clear_custom_patterns(VALUE self);
+VALUE rb_custom_patterns(VALUE self);
+
+#endif