gigatoken 0.3.0 → 0.5.0

data/lib/gigatoken/hub.rb

@@ -2,6 +2,7 @@
 
 require "async"
 require "async/http"
+require "async/http/proxy"
 require "fileutils"
 require "pathname"
 
@@ -32,6 +33,39 @@ module Gigatoken
     MAX_REDIRECTS = 10
     private_constant :MAX_REDIRECTS
 
+    # Connect/read timeout in seconds, and the bound on the request phase —
+    # huggingface_hub's HF_HUB_ETAG_TIMEOUT / HF_HUB_DOWNLOAD_TIMEOUT
+    # default.
+    DEFAULT_TIMEOUT = 10
+    private_constant :DEFAULT_TIMEOUT
+
+    # A "." or ".." path segment: the traversal that must never reach a URL
+    # or the cache, wherever it comes from.
+    DOT_SEGMENT = /\A\.\.?\z/
+    private_constant :DOT_SEGMENT
+
+    # Everything outside RFC 3986's unreserved set, which is what
+    # huggingface_hub's `quote` percent-encodes.
+    RESERVED = /[^A-Za-z0-9\-._~]/
+    private_constant :RESERVED
+
+    # How a request, or the body read that follows it, fails underneath
+    # async-http: a connect/read timeout, a refused or reset connection, a
+    # proxy refusing the CONNECT tunnel, DNS resolution, a body cut short, a
+    # malformed endpoint, TLS. All of them reach the caller as
+    # Gigatoken::HubError.
+    TRANSPORT_ERRORS = [
+      Async::TimeoutError,
+      Async::HTTP::Proxy::ConnectFailure,
+      IOError,
+      SocketError,
+      SystemCallError,
+      URI::InvalidURIError,
+      Protocol::HTTP::Error,
+      OpenSSL::SSL::SSLError
+    ].freeze
+    private_constant :TRANSPORT_ERRORS
+
     class << self
       # Whether `name` is shaped like a HuggingFace Hub repo id: `org/name`,
       # or a bare legacy repo name like `gpt2`. At most one slash, and not
@@ -105,15 +139,44 @@ module Gigatoken
         env("HF_ENDPOINT") || DEFAULT_ENDPOINT
       end
 
+      # Whether `value` is usable as a URL path and a cache path component:
+      # not empty, not absolute, no NUL byte, no "." or ".." segment.
+      # huggingface_hub rejects the same traversals in validate_repo_id.
+      def safe_component?(value)
+        !value.empty? && !value.include?("\0") && !value.start_with?("/") &&
+          value.split("/", -1).none? { |segment| segment.match?(DOT_SEGMENT) }
+      end
+
+      # The proxy URL the environment names for a `scheme` request to
+      # `hostname`, or nil: http_proxy/https_proxy, lowercase spelling
+      # first, suppressed by a matching no_proxy entry — what requests does,
+      # and so what huggingface_hub inherits.
+      def proxy_url(scheme, hostname)
+        url = env("#{scheme}_proxy") || env("#{scheme.upcase}_PROXY")
+        url unless url.nil? || no_proxy?(hostname)
+      end
+
       private
 
+      # no_proxy is a comma-separated list of host suffixes, or "*" for
+      # everything.
+      def no_proxy?(hostname)
+        host = hostname.downcase
+        (env("no_proxy") || env("NO_PROXY")).to_s.split(",").any? do |entry|
+          entry = entry.strip.downcase.delete_prefix(".")
+          next true if entry == "*"
+
+          !entry.empty? && (host == entry || host.end_with?(".#{entry}"))
+        end
+      end
+
       def env(key)
         value = ENV[key]
         value unless value.nil? || value.empty?
       end
 
       def word_part?(part, first_alnum:)
-        return false if part.nil? || part.empty?
+        return false if part.nil? || part.empty? || part.match?(DOT_SEGMENT)
 
         first_ok = first_alnum ? part[0].match?(/[A-Za-z0-9]/) : word_char?(part[0])
         first_ok && part[1..].chars.all? { |c| word_char?(c) }
@@ -133,14 +196,26 @@ module Gigatoken
     #   for pointing at a local server in tests (dependency injection, not a
     #   mock); defaults to Hub.default_endpoint (HF_ENDPOINT, then
     #   huggingface.co).
-    def initialize(endpoint: self.class.default_endpoint)
+    # @parameter timeout [Numeric] connect/read timeout in seconds, applied
+    #   to every request and to the request phase as a whole.
+    def initialize(endpoint: self.class.default_endpoint, timeout: DEFAULT_TIMEOUT)
       @endpoint = endpoint.chomp("/")
-      @internet = Async::HTTP::Internet.new
+      @timeout = timeout
     end
 
     # Path of `filename` from Hub repo `repo_id` at `revision`, served from
-    # the standard HF cache, downloading into it first when absent.
+    # the standard HF cache, downloading into it first when absent. The
+    # three caller-supplied components are checked before any request or
+    # filesystem access: one of them carrying `..` would otherwise read and
+    # overwrite files outside the cache.
     def hub_file(repo_id, filename = "tokenizer.json", revision: "main")
+      {"repo id" => repo_id, "filename" => filename, "revision" => revision}.each do |what, value|
+        next if self.class.safe_component?(value)
+
+        raise HubError, "#{what} #{value.inspect}: must not be empty or absolute, " \
+          "or contain a NUL byte or a \".\" or \"..\" path segment"
+      end
+
       self.class.cached_file(repo_id, filename, revision) ||
         Sync { fetch(repo_id, filename, revision) }
     end
@@ -152,31 +227,127 @@ module Gigatoken
     # recording the branch ref so later lookups (ours and
     # huggingface_hub's) resolve it.
     def fetch(repo_id, filename, revision)
-      url = "#{@endpoint}/#{repo_id}/resolve/#{revision}/#{filename}"
+      clients = []
+      url = resolve_url(repo_id, filename, revision)
       token = self.class.hf_token
-      response = @internet.get(url, auth_headers(token))
+      headers = auth_headers(token)
+      response = get(url, headers, clients)
       # Unlisted headers parse as a Header::Generic (an Array of values);
       # x-repo-commit is always a single value, so flatten it to a String.
       commit = response.headers["x-repo-commit"]&.to_s
 
-      # Redirects are followed by hand: resolve/ URLs answer with the
-      # x-repo-commit header and a redirect to a CDN for LFS files, and the
-      # Authorization header must not travel to the other host.
+      # Redirects are followed by hand: a resolve/ URL answers an LFS file
+      # with a redirect to a CDN, a renamed repo with one to its new name,
+      # and both headers below need a rule of their own across the hop.
       hops = 0
       while (300...400).cover?(response.status)
-        ensure_ok!(url, response.status, !!token)
-        hops += 1
-        raise Error, "#{url}: too many redirects" if hops > MAX_REDIRECTS
-
-        location = response.headers["location"] ||
-          raise(Error, "#{url}: redirect with no Location header")
+        location = response.headers["location"]
         response.close
-        url = absolutize(location, url)
-        response = @internet.get(url, {"user-agent" => "gigatoken"})
+        raise HubError, "#{url}: redirect with no Location header" unless location
+        raise HubError, "#{url}: too many redirects" if (hops += 1) > MAX_REDIRECTS
+
+        target = absolutize(location, url)
+        # A renamed repo answers with a same-origin redirect that still needs
+        # the token; the LFS CDN elsewhere authenticates by signed URL and
+        # must never see it — huggingface_hub drops the header on the same
+        # rule.
+        headers = auth_headers(nil) unless same_origin?(target, url)
+        url = target
+        response = get(url, headers, clients)
+        # An LFS file carries x-repo-commit on the resolve/ hop; a renamed
+        # repo carries it only on the hop that finally answers 200.
+        commit ||= response.headers["x-repo-commit"]&.to_s
       end
-      ensure_ok!(url, response.status, !!token)
+      ensure_ok!(url, response, !!token)
+      ensure_commit!(url, commit)
+
+      write_to_cache(repo_id, filename, revision, commit, response)
+    rescue *TRANSPORT_ERRORS => e
+      raise HubError, "#{url}: #{e.message} (#{e.class})"
+    ensure
+      close_all(response, clients)
+    end
 
-      write_to_cache(repo_id, filename, revision, commit || revision, response)
+    # Release everything the fetch holds, in the one place every exit passes
+    # through. Order matters: an unread body keeps its connection checked
+    # out, and Async::HTTP::Client#close waits for its pool to drain, so the
+    # response goes first and the clients innermost-first — a tunnel client's
+    # connection is held by the proxy client opened under it. Bounded, and
+    # deaf to the ways a broken connection fails to close: a connection some
+    # failure left mid-stream would otherwise stall the drain, and with it
+    # the Sync this all runs inside, for good. A leaked socket is worth less
+    # than the caller's result or exception.
+    def close_all(response, clients)
+      Async::Task.current.with_timeout(@timeout) do
+        response&.close
+        clients.reverse_each(&:close)
+      end
+    rescue *TRANSPORT_ERRORS
+      nil
+    end
+
+    # `endpoint/repo/resolve/revision/filename`, percent-encoded the way
+    # huggingface_hub's `quote` does it: `revision` whole (`safe=""`), so
+    # `refs/pr/1` travels as `refs%2Fpr%2F1`, while the repo id and the
+    # filename keep their slashes.
+    def resolve_url(repo_id, filename, revision)
+      "#{@endpoint}/#{escape_path(repo_id)}/resolve/#{escape(revision)}/#{escape_path(filename)}"
+    end
+
+    def escape_path(value)
+      value.split("/", -1).map { |segment| escape(segment) }.join("/")
+    end
+
+    def escape(value)
+      value.gsub(RESERVED) { |char| char.bytes.map { |byte| format("%%%02X", byte) }.join }
+    end
+
+    # GET `url`, through the proxy the environment names for it when there
+    # is one: an http request travels to the proxy with the absolute URI in
+    # its request line, an https one through a CONNECT tunnel — how requests,
+    # and so huggingface_hub, routes them. The clients stay open (the body
+    # is still to be streamed); #fetch closes them.
+    def get(url, headers, clients)
+      endpoint = endpoint_for(url)
+      proxy = self.class.proxy_url(endpoint.scheme, endpoint.hostname)
+      proxy &&= endpoint_for(proxy)
+
+      client =
+        if proxy.nil?
+          open_client(endpoint, clients)
+        elsif endpoint.secure?
+          # https tunnels through the proxy with CONNECT, then speaks TLS to
+          # the origin as if it had connected to it directly.
+          open_client(open_client(proxy, clients).proxied_endpoint(endpoint), clients)
+        else
+          open_client(proxy, clients)
+        end
+      # An http proxy is addressed with the absolute URI in the request line;
+      # a direct or tunnelled request carries just the path.
+      target = (proxy && !endpoint.secure?) ? url : endpoint.path
+
+      request = Protocol::HTTP::Request["GET", target, headers, scheme: endpoint.scheme, authority: endpoint.authority]
+      # A CONNECT tunnel's socket carries no timeout of its own, so the
+      # request phase is bounded here whichever way it was routed; the body
+      # then streams under the endpoint's own connect/read timeout.
+      Async::Task.current.with_timeout(@timeout) { client.call(request) }
+    end
+
+    # A malformed URL comes back as URI::InvalidURIError, one that cannot be
+    # routed (no scheme or host) as ArgumentError; both mean the same thing
+    # to the caller, and neither is worth a backtrace.
+    def endpoint_for(url)
+      Async::HTTP::Endpoint.parse(url, timeout: @timeout)
+    rescue ArgumentError => e
+      raise HubError, "#{url}: #{e.message} (#{e.class})"
+    end
+
+    # A client for one hop, remembered in `clients` so #fetch can close it
+    # once the body is written. retries: 1 — a client built for this hop has
+    # no stale pooled connection for a retry to rescue, and async-http's
+    # default of 3 would pay @timeout three times over.
+    def open_client(endpoint, clients)
+      Async::HTTP::Client.new(endpoint, retries: 1).tap { |client| clients << client }
     end
 
     def auth_headers(token)
@@ -199,51 +370,75 @@ module Gigatoken
       rescue
         FileUtils.rm_f(tmp)
         raise
-      ensure
-        response.close
       end
       File.rename(tmp, target)
 
-      if !self.class.commit_hash?(revision) && revision != commit
-        refs_dir = repo_dir.join("refs")
-        FileUtils.mkdir_p(refs_dir)
-        File.write(refs_dir.join(revision), commit)
+      # A nested revision like refs/pr/1 is a nested ref file, so its parent
+      # has to exist — huggingface_hub mkdir -p's the same path.
+      if revision != commit
+        ref_path = repo_dir.join("refs", revision)
+        FileUtils.mkdir_p(ref_path.dirname)
+        File.write(ref_path, commit)
       end
 
       target
     end
 
-    def ensure_ok!(url, status, had_token)
+    # Raise on a non-success status. The unread body is left to #close_all,
+    # which every exit from #fetch passes through: it keeps the HTTP/1.x
+    # connection — and the Sync around it — alive until it is closed, so the
+    # exception would otherwise never reach the caller.
+    def ensure_ok!(url, response, had_token)
+      status = response.status
       return if (200...400).cover?(status)
 
       case status
       when 404
-        raise Error, "#{url}: HTTP 404 — no such repo with that file, and no such local file either"
+        raise HubError, "#{url}: HTTP 404 — no such repo with that file, and no such local file either"
       when 401, 403
         token_note = had_token ? "the request used the discovered token" : "no token was found"
-        raise Error,
+        raise HubError,
           "#{url}: HTTP #{status} — the repo may be private or gated (#{token_note}; set HF_TOKEN or run " \
           "`hf auth login`, and accept the repo's terms on huggingface.co if it is gated)"
       else
-        raise Error, "#{url}: HTTP #{status}"
+        raise HubError, "#{url}: HTTP #{status}"
       end
     end
 
+    # The snapshot directory is named by a server-controlled header, so only
+    # a real commit hash may become one: anything else would write the body
+    # wherever the header points. A missing header also means the endpoint
+    # isn't a Hub, whose snapshot would never be found again.
+    def ensure_commit!(url, commit)
+      return if self.class.commit_hash?(commit.to_s)
+
+      raise HubError, "#{url}: response is missing a usable x-repo-commit header (#{commit.inspect}) — it does not " \
+        "seem to be served by a HuggingFace Hub endpoint; if HF_ENDPOINT is set, check that it points to a " \
+        "Hub-compatible endpoint, and otherwise check your firewall and proxy settings"
+    end
+
     # A redirect Location resolved against the request URL: absolute URLs
     # pass through, host-relative (`/x/y`) and path-relative ones join the
     # base.
     def absolutize(location, base)
       return location if location.include?("://")
 
-      origin_end = base.index("://") ? base.index("://") + 3 : 0
-      origin_end = base.index("/", origin_end) || base.length
+      base_origin = origin(base)
+      return "#{base_origin}#{location}" if location.start_with?("/")
 
-      if location.start_with?("/")
-        "#{base[0...origin_end]}#{location}"
-      else
-        dir_end = base.rindex("/") || base.length
-        "#{base[0...[dir_end, origin_end].max]}/#{location}"
-      end
+      dir_end = base.rindex("/") || base.length
+      "#{base[0...[dir_end, base_origin.length].max]}/#{location}"
+    end
+
+    # Scheme and authority of a URL — everything before its path. Two URLs
+    # sharing one may pass the Authorization header between them.
+    def origin(url)
+      scheme_end = url.index("://")
+      url[0...(url.index("/", scheme_end ? scheme_end + 3 : 0) || url.length)]
+    end
+
+    def same_origin?(url, other)
+      origin(url).casecmp?(origin(other))
     end
   end
 end

data/lib/gigatoken/packed_result.rb

@@ -29,8 +29,12 @@ module Gigatoken
     end
 
     # Array of token ids for document `i`, materialized on demand; negative
-    # indices count from the end and out-of-range ones give nil, like Array.
-    def [](i)
+    # indices count from the end, out-of-range ones give nil, and a
+    # non-Integer index is a TypeError, all like Array.
+    def [](index)
+      i = Integer.try_convert(index)
+      raise TypeError, "no implicit conversion of #{index.class} into Integer" if i.nil?
+
       i += size if i.negative?
       return unless i >= 0 && i < size
 

data/lib/gigatoken/tokenizer.rb

@@ -1,6 +1,7 @@
 # frozen_string_literal: true
 
 require "json"
+require "zlib"
 
 module Gigatoken
   # A tokenizer: encode, batch encode, decode, and vocabulary introspection
@@ -10,18 +11,35 @@ module Gigatoken
     FILE_SOURCE_CLASSES = [Native::TextFileSource, Native::JsonlFileSource, Native::ParquetFileSource].freeze
     private_constant :FILE_SOURCE_CLASSES
 
+    # Encodings whose bytes reach the native call untouched. UTF-8 is checked
+    # by identity first — it is the hot path, see #encode — and these are the
+    # rest: US-ASCII already is UTF-8 bytes, and ASCII-8BIT is deliberately
+    # raw bytes. Anything else — ISO-8859-1, Windows-1252, UTF-16LE — is a
+    # real encoding whose bytes are not the text's UTF-8 bytes, so encoding it
+    # raw would give different ids than the same text read as UTF-8. (Invalid
+    # bytes in a UTF-8-tagged String stay raw: a documented difference from
+    # tiktoken, which rejects them.)
+    BYTEWISE_ENCODINGS = [Encoding::US_ASCII, Encoding::BINARY].freeze
+    private_constant :BYTEWISE_ENCODINGS
+
     # Load from in-memory tokenizer.json contents (String or bytes). Backed
     # by a BPETokenizer or a SentencePieceTokenizer, per the model's
-    # byte_fallback flag.
+    # byte_fallback flag. The document is parsed twice, deliberately: the Ruby
+    # parse runs first because JSON.parse's depth limit is what keeps hostile
+    # nesting away from the native parser (see parse_json), and it is also
+    # where the special-token table is read from.
     def self.from_json(data)
-      native = Native.load_hf_json(data)
-      new(native, special_tokens: special_tokens_from_json(data))
+      json = String.try_convert(data) or raise TypeError, "no implicit conversion of #{data.class} into String"
+      parsed = parse_json(json)
+      new(Native.load_hf_json(json), special_tokens: special_tokens_from(parsed))
     end
 
     # Load from a tokenizer.json path, or a directory containing one.
     def self.from_file(path)
-      path = File.join(path, "tokenizer.json") if File.directory?(path)
-      from_json(File.binread(path))
+      file = File.directory?(path) ? File.join(path, "tokenizer.json") : path.to_s
+      raise ModelError, "#{file.inspect}: no such file" unless File.file?(file)
+
+      from_json(File.binread(file))
     end
 
     # Load from a .tiktoken mergeable-ranks file. The file carries neither a
@@ -35,16 +53,18 @@ module Gigatoken
       new(native, special_tokens: special_tokens)
     end
 
-    # Load one of the tiktoken encodings gigatoken vendors ranks for, by
-    # name — see Gigatoken::Encodings::NAMES — entirely from the vendored
-    # files: no network, no writable cache.
+    # Load one of the encodings gigatoken vendors a file for, by name — see
+    # Gigatoken::Encodings::NAMES — entirely from the vendored files: no
+    # network, no writable cache. A tiktoken entry loads its ranks; a
+    # tokenizer.json entry is gunzipped and loaded by from_json.
     def self.from_encoding(name)
       encoding = Encodings[name]
+      return from_json(Zlib.gunzip(File.binread(encoding[:json_file]))) if encoding&.key?(:json_file)
       return from_tiktoken(encoding[:rank_file], pretokenizer: encoding[:pretokenizer], special_tokens: encoding[:special_tokens]) if encoding
 
       reason = Encodings.unpackable_reason(name)
       detail = reason ? " — #{reason}" : ""
-      raise Error, "#{name.inspect}: not a packaged encoding#{detail} (packaged encodings: #{Encodings::NAMES.join(", ")})"
+      raise ModelError, "#{name.inspect}: not a packaged encoding#{detail} (packaged encodings: #{Encodings::NAMES.join(", ")})"
     end
 
     # Load tokenizer.json from HuggingFace Hub repo `repo_id` at `revision`
@@ -71,7 +91,7 @@ module Gigatoken
       source = source.to_s
       if source.end_with?(".tiktoken")
         unless pretokenizer
-          raise Error, "#{source.inspect}: a .tiktoken file carries no pretokenizer scheme of its own — " \
+          raise ModelError, "#{source.inspect}: a .tiktoken file carries no pretokenizer scheme of its own — " \
             "pass pretokenizer: (one of #{Native.pretokenizer_names.join(", ")})"
         end
         return from_tiktoken(source, pretokenizer: pretokenizer, special_tokens: special_tokens)
@@ -80,25 +100,44 @@ module Gigatoken
       return from_encoding(source) if Encodings::NAMES.include?(source) || Encodings.unpackable_reason(source)
       return from_hub(source, revision: revision, hub: hub) if Hub.looks_like_repo_id?(source)
 
-      raise Error, "#{source.inspect}: no such file or directory, not a .tiktoken path, and doesn't look like a HuggingFace Hub repo id"
+      raise ModelError, "#{source.inspect}: no such file or directory, not a .tiktoken path, and doesn't look like a HuggingFace Hub repo id"
     end
 
     # `data` is UTF-8 JSON whatever its encoding tag says (File.binread tags
     # binary; a US-ASCII default_external tags that), so retag rather than let
     # JSON.parse transcode from the tag; a UTF-8-tagged String needs no copy.
-    def self.special_tokens_from_json(data)
+    # JSON.parse's default max_nesting of 100 is the guard: the native parser
+    # is recursive with no depth limit, and deep enough nesting overflows its
+    # stack rather than raising.
+    def self.parse_json(data)
       data = data.dup.force_encoding(Encoding::UTF_8) unless data.encoding == Encoding::UTF_8
-      added = JSON.parse(data)["added_tokens"] || []
+      JSON.parse(data)
+    rescue JSON::ParserError => e
+      raise ModelError, "failed to parse tokenizer JSON: #{e.message}"
+    end
+    private_class_method :parse_json
+
+    def self.special_tokens_from(parsed)
+      added = parsed["added_tokens"] || []
       added.each_with_object({}) { |t, h| h[t["content"]] = t["id"] if t["special"] }
     end
-    private_class_method :special_tokens_from_json
+    private_class_method :special_tokens_from
 
+    # The table is frozen so `#special_tokens` can neither alias the
+    # deep-frozen registry's Hash nor a `from_tiktoken` caller's; an
+    # already-frozen one is safe to share as-is.
     def initialize(native, special_tokens: {})
       @native = native
-      @special_tokens = special_tokens
+      @special_tokens = special_tokens.frozen? ? special_tokens : special_tokens.dup.freeze
     end
 
+    # A String already tagged UTF-8 — every ordinary document — reaches the
+    # native call over one inline identity check. A helper frame here is
+    # measurable against the encode itself at document sizes this small, so
+    # the check is spelled out rather than delegated to #transcode?; anything
+    # else takes the slow path in #utf8.
     def encode(text)
+      text = utf8(text) unless text.is_a?(String) && text.encoding == Encoding::UTF_8
       @native.encode(text)
     end
 
@@ -107,6 +146,7 @@ module Gigatoken
     # token ids plus per-document lengths), avoiding the per-token Ruby
     # array materialization the ragged shape costs.
     def encode_batch(texts, packed: false)
+      texts = utf8_batch(texts)
       if packed
         PackedResult.new(*@native.encode_batch_packed(texts))
       else
@@ -154,5 +194,34 @@ module Gigatoken
     end
 
     attr_reader :special_tokens
+
+    private
+
+    # UTF-8 first and by identity, so the batch walk below costs the same one
+    # comparison per document that #encode costs; the list is only consulted
+    # for the encodings that aren't it.
+    def transcode?(text)
+      text.is_a?(String) && text.encoding != Encoding::UTF_8 && !BYTEWISE_ENCODINGS.include?(text.encoding)
+    end
+
+    # A transcode that can't be done — a dummy encoding like UTF-7, bytes the
+    # tag doesn't allow, a character the target can't hold — is a fact about
+    # the document, not about the tokenizer, and reaches the caller as one.
+    def utf8(text)
+      transcode?(text) ? text.encode(Encoding::UTF_8) : text
+    rescue EncodingError => e
+      raise InputError, e.message
+    end
+
+    # The same rule per document, without copying the Array when — as in
+    # every UTF-8 batch — there is nothing to transcode. Elements are only
+    # type-checked, never coerced: a `to_str` object is left for the native
+    # side to convert under its own snapshot of the input.
+    def utf8_batch(texts)
+      array = Array.try_convert(texts)
+      return texts if array.nil? || array.none? { |text| transcode?(text) }
+
+      array.map { |text| utf8(text) }
+    end
   end
 end

data/lib/gigatoken/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Gigatoken
-  VERSION = "0.3.0"
+  VERSION = "0.5.0"
 end

data/lib/gigatoken.rb

@@ -4,9 +4,25 @@ require_relative "gigatoken/version"
 
 module Gigatoken
   # Raised for tokenizer load and encode failures surfaced from the native
-  # extension — never a raw Rust panic across the Ruby boundary.
+  # extension — never a raw Rust panic across the Ruby boundary. The base of
+  # the three below: rescue this to catch everything gigatoken raises.
+  # Anything narrower than the three has no class of its own — CLI usage
+  # errors and the odd leftover are this one directly.
   class Error < StandardError; end
 
+  # Everything Gigatoken::Hub raises: HTTP status, transport, timeout, repo-id
+  # / revision / filename / x-repo-commit validation.
+  class HubError < Error; end
+
+  # A document the tokenizer cannot take: an untranscodable or invalid-byte
+  # String, invalid UTF-8 on the SentencePiece path, an id outside the
+  # vocabulary in #decode.
+  class InputError < Error; end
+
+  # A tokenizer that cannot be loaded: bad or hostile JSON, a missing file or
+  # directory, an unknown or unpackable encoding name, a malformed .tiktoken.
+  class ModelError < Error; end
+
   class << self
     # The process-global encode-cache budget in bytes per worker (a parallel
     # batch encode may use up to workers x budget), applied to tokenizers of