mq-ruby 0.1.28 → 0.1.30

data/Cargo.toml

@@ -10,7 +10,7 @@ name = "mq-ruby"
 publish = false
 readme = "README.md"
 repository = "https://github.com/harehare/mq"
-version = "0.1.28"
+version = "0.1.30"
 
 [lib]
 crate-type = ["cdylib"]
@@ -18,6 +18,10 @@ name = "mq_ruby"
 
 [dependencies]
 magnus = {version = "0.8"}
-mq-lang = "0.6.4"
-mq-markdown = "0.6.4"
+mq-lang = {version = "0.7.0", features = ["css-selector"]}
+mq-markdown = "0.7.0"
+# Pinned below the rb-sys releases (0.9.120+) that added Ruby 4.x-specific
+# ABI handling, which is buggy on Ruby 4.0 under magnus 0.8.2 and breaks
+# TypedData class conversion (see MQ::Result CI failures on Ruby 4.0).
+rb-sys = "=0.9.117"
 

data/README.md

@@ -254,6 +254,7 @@ MQ::Query.list.map { contains("important") }
 .to_html           # to_html()          — HTML string
 .to_string         # to_string()        — string coercion
 .to_number         # to_number()        — numeric coercion
+.to_boolean        # to_boolean()       — boolean coercion
 .to_array          # to_array()
 .to_bytes          # to_bytes()
 .to_markdown_string # to_markdown_string()
@@ -267,22 +268,34 @@ MQ::Query.list.map { contains("important") }
 .rtrim             # rtrim()
 .downcase          # downcase()
 .upcase            # upcase()
+.ascii_downcase    # ascii_downcase()
+.ascii_upcase      # ascii_upcase()
 .len               # len()
 .utf8bytelen       # utf8bytelen()
 .explode           # explode()          — string to codepoints
 .implode           # implode()          — codepoints to string
 .url_encode        # url_encode()
+.url_decode        # url_decode()
 .intern            # intern()
+.html_escape       # html_escape()
+.html_unescape     # html_unescape()
+.sanitize_html     # sanitize_html()   — strip dangerous tags/attrs
+.strip_tags        # strip_tags()      — remove all HTML tags
 
 .split(",")        # split(",")
 .gsub("pat", "r")  # gsub("pat", "r")  — regex replace all
 .replace("a", "b") # replace("a", "b") — literal replace
 .test("\\d+")      # test("\\d+")      — regex test → bool
 .capture("(\\w+)") # capture("(\\w+)") — regex capture
+.scan("(\\w+)")    # scan("(\\w+)")    — all regex matches
 .slice(0, 5)       # slice(0, 5)
 .index("sub")      # index("sub")      — position of substring
 .rindex("sub")     # rindex("sub")     — last position
 .repeat(3)         # repeat(3)
+.word_wrap(20)     # word_wrap(20)     — wrap text to column width
+.truncate(10, "…") # truncate(10, "…") — shorten with an ellipsis
+.token_count       # token_count()     — estimate LLM token count
+.token_count("gpt-4") # token_count("gpt-4")
 ```
 
 #### Collection Operations
@@ -309,6 +322,8 @@ MQ::Query.list.map { contains("important") }
 .range(3)          # range(3)
 .del("key")        # del("key")
 .insert(0, "val")  # insert(0, "val")
+.shuffle           # shuffle()         — random order
+.sample(3)         # sample(3)         — n random elements, no replacement
 ```
 
 #### Math Operations
@@ -350,8 +365,18 @@ MQ::Query.list.map { contains("important") }
 .sha512            # sha512()
 .from_hex          # from_hex()
 .to_hex            # to_hex()
+.uuid              # uuid()            — random (v4) UUID
+.uuid_v4           # uuid_v4()         — alias of uuid
+.uuid_v7           # uuid_v7()         — time-ordered (v7) UUID
+.rand              # rand()            — pseudo-random number in [0, 1)
+.rand_int(1, 10)   # rand_int(1, 10)   — pseudo-random integer in [min, max]
 ```
 
+`MQ::Query.uuid`, `.uuid_v4`, `.uuid_v7`, `.rand`, `.rand_int(min, max)`, and
+`.random_string(len, charset)` are also available as class-level generators to
+start a query without a preceding selector, e.g. `MQ::Query.uuid.to_query # =>
+"uuid()"`.
+
 #### Path Operations
 
 ```ruby
@@ -360,14 +385,30 @@ MQ::Query.list.map { contains("important") }
 .extname           # extname()
 .stem              # stem()
 .path_join("sub")  # path_join("sub")
+.glob_match("docs/readme.md") # glob_match("docs/readme.md") — self is the glob pattern
+```
+
+#### HTML / CSS Selector Operations
+
+Query a raw HTML string directly with a CSS selector, bypassing Markdown
+conversion — useful for tags/classes/ids/`data-*` attributes that would
+otherwise be lost.
+
+```ruby
+.css("p.intro")        # css("p.intro")        — outer HTML of matches
+.css_text("p.intro")   # css_text("p.intro")   — text content of matches
+.css_attr("a", "href") # css_attr("a", "href") — attribute value of matches
 ```
 
 #### Dict Operations
 
 ```ruby
-.get("key")            # get("key")
-.set("key", "val")     # set("key", "val")
-.property("key")       # ."key"
+.get("key")                     # get("key")
+.set("key", "val")              # set("key", "val")
+.property("key")                # ."key"
+.get_path(["a", "b"])           # get_path(["a", "b"])
+.set_path(["a", "b"], "val")    # set_path(["a", "b"], "val")
+.paths                          # paths()           — array of leaf-path arrays
 ```
 
 #### Markdown Attribute Operations

data/lib/mq/query.rb

@@ -66,6 +66,7 @@ module MQ
     def to_html        = pipe_with("to_html()")
     def to_string      = pipe_with("to_string()")
     def to_number      = pipe_with("to_number()")
+    def to_boolean     = pipe_with("to_boolean()")
     def to_array       = pipe_with("to_array()")
     def to_bytes       = pipe_with("to_bytes()")
     def to_markdown_string = pipe_with("to_markdown_string()")
@@ -135,15 +136,42 @@ module MQ
       pipe_with("repeat(#{n})")
     end
 
+    def shuffle        = pipe_with("shuffle()")
+
+    def sample(n)
+      pipe_with("sample(#{n})")
+    end
+
     def trim           = pipe_with("trim()")
     def ltrim          = pipe_with("ltrim()")
     def rtrim          = pipe_with("rtrim()")
     def downcase       = pipe_with("downcase()")
     def upcase         = pipe_with("upcase()")
+    def ascii_downcase = pipe_with("ascii_downcase()")
+    def ascii_upcase   = pipe_with("ascii_upcase()")
     def explode        = pipe_with("explode()")
     def implode        = pipe_with("implode()")
     def url_encode     = pipe_with("url_encode()")
+    def url_decode     = pipe_with("url_decode()")
     def intern         = pipe_with("intern()")
+    def html_escape    = pipe_with("html_escape()")
+    def html_unescape  = pipe_with("html_unescape()")
+    def sanitize_html  = pipe_with("sanitize_html()")
+    def strip_tags     = pipe_with("strip_tags()")
+
+    def word_wrap(width)
+      pipe_with("word_wrap(#{width})")
+    end
+
+    def truncate(len, ellipsis)
+      pipe_with("truncate(#{len}, #{ellipsis.inspect})")
+    end
+
+    # Estimates (or, when mq was built with tiktoken support, exactly counts) the
+    # LLM tokens the current string would consume. +model+ is optional.
+    def token_count(model = nil)
+      model ? pipe_with("token_count(#{model.inspect})") : pipe_with("token_count()")
+    end
 
     def gsub(pattern, replacement)
       pipe_with("gsub(#{pattern.inspect}, #{replacement.inspect})")
@@ -161,6 +189,10 @@ module MQ
       pipe_with("capture(#{pattern.inspect})")
     end
 
+    def scan(pattern)
+      pipe_with("scan(#{pattern.inspect})")
+    end
+
     def abs            = pipe_with("abs()")
     def ceil           = pipe_with("ceil()")
     def floor          = pipe_with("floor()")
@@ -205,6 +237,15 @@ module MQ
     def to_hex         = pipe_with("to_hex()")
     def to_hex_str     = pipe_with("to_hex()")
 
+    def uuid           = pipe_with("uuid()")
+    def uuid_v4        = pipe_with("uuid_v4()")
+    def uuid_v7        = pipe_with("uuid_v7()")
+    def rand           = pipe_with("rand()")
+
+    def rand_int(min, max)
+      pipe_with("rand_int(#{min}, #{max})")
+    end
+
     def basename       = pipe_with("basename()")
     def dirname        = pipe_with("dirname()")
     def extname        = pipe_with("extname()")
@@ -214,6 +255,30 @@ module MQ
       pipe_with("path_join(#{other.inspect})")
     end
 
+    # Treats the current string as a glob pattern (e.g. "*.md", "docs/**/*.rs")
+    # and returns whether it matches +path+.
+    def glob_match(path)
+      pipe_with("glob_match(#{path.inspect})")
+    end
+
+    # Returns the outer HTML of every element in the current (raw) HTML string
+    # matching the CSS +selector+, as an array of strings.
+    def css(selector)
+      pipe_with("css(#{selector.inspect})")
+    end
+
+    # Returns the text content of every element in the current (raw) HTML
+    # string matching the CSS +selector+, as an array of strings.
+    def css_text(selector)
+      pipe_with("css_text(#{selector.inspect})")
+    end
+
+    # Returns the value of attribute +name+ for every element in the current
+    # (raw) HTML string matching the CSS +selector+, as an array.
+    def css_attr(selector, name)
+      pipe_with("css_attr(#{selector.inspect}, #{name.inspect})")
+    end
+
     def get(key)
       pipe_with("get(#{key.inspect})")
     end
@@ -222,6 +287,22 @@ module MQ
       pipe_with("set(#{key.inspect}, #{val.inspect})")
     end
 
+    # Retrieves a nested value by following an array of keys/indices.
+    def get_path(path)
+      pipe_with("get_path(#{path.inspect})")
+    end
+
+    # Sets a nested value by following an array of keys/indices, creating
+    # missing intermediate dicts/arrays automatically.
+    def set_path(path, new_value)
+      pipe_with("set_path(#{path.inspect}, #{new_value.inspect})")
+    end
+
+    # Returns an array of leaf-path arrays for the current value.
+    def paths
+      pipe_with("paths()")
+    end
+
     # Access a dict property by key (generates ."key" selector)
     def property(key)
       pipe_with(".\"#{key}\"")
@@ -453,6 +534,22 @@ module MQ
 
       def to_text     = new("to_text()")
       def to_markdown = new("to_markdown()")
+
+      # --- Value generators (usable as query starting points) ---
+      def uuid        = new("uuid()")
+      def uuid_v4     = new("uuid_v4()")
+      def uuid_v7     = new("uuid_v7()")
+      def rand        = new("rand()")
+
+      def rand_int(min, max)
+        new("rand_int(#{min}, #{max})")
+      end
+
+      # Returns a random string of +len+ characters drawn (with replacement)
+      # from +charset+.
+      def random_string(len, charset)
+        new("random_string(#{len}, #{charset.inspect})")
+      end
     end
 
     private

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: mq-ruby
 version: !ruby/object:Gem::Version
-  version: 0.1.28
+  version: 0.1.30
 platform: ruby
 authors:
 - Takahiro Sato
@@ -72,6 +72,7 @@ extensions:
 - extconf.rb
 extra_rdoc_files: []
 files:
+- Cargo.lock
 - Cargo.toml
 - LICENSE
 - README.md