simple_english 0.2.0 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 18c24cb1079203715bb6c9decdf37cbae2221ef7db6ce93cc91cea6cd40e80ec
-  data.tar.gz: 25c81010ee8974bc23393acb0e7b692634616122201ca693e12a979ef310bf53
+  metadata.gz: 5c1efe5da86f44ce1618aea7d2c49f3e5dd0aec897a8f103ace5276be73d9ef4
+  data.tar.gz: cd8597b07d037a0631d16ea11377144fb9b93d6f6e604a316027d5c43a72d50d
 SHA512:
-  metadata.gz: 85550424bc3b8cbd339180ba2f1c91a3125690af0bebb8b11efdf4d367569b15952cff57122e3c768989d8233c4daa23eb4f8359e6a2ce20a1ba5b9471ef1f12
-  data.tar.gz: 7a51bf55350c8b34501c5a0537236890ab8783d1199cc8c57e84bd3f3d24107aafa2e8e2944e49e909601f5a33e5ed1f11cb9812e9f5bb500aea05e60bc6db3e
+  metadata.gz: 838420d06071034d7e6d48c074fc0d5893b6443e6f1dd387247e86239f74b620ff7e4adecd69e4b37a3d58e98ebb193bbe53a113dc96759a075cb08fdd8247c7
+  data.tar.gz: 7fcc415dcf6cc5a01ba01807118ca6e3ea8ff7f7d4573960f5b31fe7971c3612559e15d5f7ee0c122363cdf2b620b8ede79ed7b0e0e193dd188a0446483045fc

data/README.md

@@ -11,16 +11,18 @@ the slop it leaves behind. Every finding says what to write
 instead.
 
 ```console
-$ printf 'You should leverage this tool in order to make sure that your docs are readable.' > note.md
+$ printf "The config was written by setup — don't edit it; the daemon caches rules, making the first lint slow." > note.md
 $ se note.md
-note.md:1:5: [SE_MODAL_RESTRICTED] "should" - Use can, will, or must. State the requirement exactly.
-note.md:1:12: [SE_SLOP_LEVERAGE] "leverage" - Write "use".
-note.md:1:31: [SE_SLOP_IN_ORDER_TO] "in order to" - Write "to".
+note.md:1:12-26: [SE_ACTIVE_VOICE] "was written by" - Use the active voice. Say who does the action.
+note.md:1:73-81: [SE_ING_AFTER_COMMA] ", making" - Start a new sentence instead of the -ing phrase.
+note.md:1:37-40: [SE_NO_CONTRACTIONS] "n't" - Write the words in full. No contractions.
+note.md:1:33-34: [SE_NO_EMDASH] "—" - Write two sentences, or use a comma.
+note.md:1:48-49: [SE_NO_SEMICOLON] ";" - Write two sentences, or name the relation.
 ```
 
 Markdown prose plus code comments in Python, Ruby, JavaScript,
-TypeScript, Go, Rust, Java, C#, Kotlin, bash, and YAML. Output as plain
-text, JSON, or SARIF.
+TypeScript, Go, Rust, Java, C#, C++, Kotlin, bash, and YAML. Output as
+plain text, JSON, or SARIF.
 
 ## The rules
 
@@ -31,7 +33,7 @@ text, JSON, or SARIF.
 - **Contractions:** write every word in full.
 - **Sentence shape:** condition before command, no `-ing` phrase after a comma.
 - **Word choice:** about 50 substitution rules, from `leverage` to `in conclusion`. `make sure that` keeps its "that".
-- **Code comments:** same pattern rules, with line and column.
+- **Code comments:** same pattern rules, with line and column range.
 - **Counts (Markdown only):** 20 words per sentence in list items, 25 in paragraphs, six sentences per paragraph at most.
 
 The full list, with a wrong and a right example for each rule:
@@ -93,7 +95,11 @@ git diff --name-only --diff-filter=ACM main | xargs se
 
 ### Outputs
 
-Findings print as `file:line: [RULE_ID] message`. Code-comment findings also carry a column in `--format json` and `--format sarif`:
+Pattern findings print an exclusive column range as
+`file:line:start-end: [RULE_ID] message`. A range that crosses lines ends
+with `end-line:end-column`. Columns count UTF-16 code units. Counting findings
+identify only the paragraph's first line. JSON and SARIF output expose the same
+source ranges:
 
 ```bash
 se --format json docs/
@@ -180,7 +186,7 @@ Any tool or language can lint through its HTTP API:
 
 ```bash
 curl -d "text=Don't do this." http://localhost:8181/lint
-# [{"line":1,"column":null,"rule":"SE_NO_CONTRACTIONS","message":"..."}]
+# [{"line":1,"column":3,"end_line":1,"end_column":6,"rule":"SE_NO_CONTRACTIONS","message":"..."}]
 ```
 
 The full wire format: [docs/DAEMON.md](docs/DAEMON.md).

data/lib/simple_english/cli.rb

@@ -122,6 +122,7 @@ module SimpleEnglish
       when "json"
         puts JSON.pretty_generate(results.map do |path, finding|
           {"path" => path, "line" => finding.line, "column" => finding.column,
+           "end_line" => finding.end_line, "end_column" => finding.end_column,
            "rule" => finding.rule, "message" => finding.message}
         end)
       when "sarif"
@@ -129,10 +130,17 @@ module SimpleEnglish
           "version" => "2.1.0",
           "$schema" => "https://json.schemastore.org/sarif-2.1.0.json",
           "runs" => [{
+            "columnKind" => "utf16CodeUnits",
             "tool" => {"driver" => {"name" => "se"}},
             "results" => results.map do |path, finding|
               region = {"startLine" => finding.line}
-              region["startColumn"] = finding.column if finding.column
+              if finding.column
+                region["startColumn"] = finding.column
+                if finding.end_line && finding.end_column
+                  region["endLine"] = finding.end_line
+                  region["endColumn"] = finding.end_column
+                end
+              end
               {"ruleId" => finding.rule, "level" => "error",
                "message" => {"text" => finding.message},
                "locations" => [{"physicalLocation" => {
@@ -145,7 +153,14 @@ module SimpleEnglish
       else
         results.each do |path, finding|
           location = "#{path}:#{finding.line}"
-          location << ":#{finding.column}" if finding.column
+          if finding.column
+            location += ":#{finding.column}"
+            if finding.end_line && finding.end_column
+              finish = (finding.end_line == finding.line) ? finding.end_column :
+                "#{finding.end_line}:#{finding.end_column}"
+              location += "-#{finish}"
+            end
+          end
           puts "#{location}: [#{finding.rule}] #{finding.message}"
         end
       end

data/lib/simple_english/client.rb

@@ -14,39 +14,23 @@ module SimpleEnglish
   module Client
     module_function
 
-    # LanguageTool reports offsets in Java UTF-16 code units.
-    # Astral characters (emoji) count as two. Count them so a
-    # newline comparison cannot drift past a boundary. A match
-    # starting at the newline itself belongs to the next line.
-    def offset_to_line(text, offset)
+    # LanguageTool reports offsets and lengths in Java UTF-16 code units.
+    # Return a 1-based line and UTF-16 column for its 0-based offset.
+    def offset_to_position(text, offset)
       line = 1
+      column = 1
       units = 0
       text.each_char do |char|
-        line += 1 if char == "\n" && units <= offset
-        return line if units >= offset
+        return [line, column] if units >= offset
         units += (char.ord > 0xFFFF) ? 2 : 1
-      end
-      line
-    end
-
-    # The 1-based column of a UTF-16 offset within its line. Astral
-    # characters count as two units, like the match offset. A match
-    # starting at the newline itself is column one of the next line.
-    def offset_to_column(text, offset)
-      column = 0
-      units = 0
-      text.each_char do |char|
         if char == "\n"
-          return 1 if units >= offset
-          column = 0
-          units += 1
-          next
+          line += 1
+          column = 1
+        else
+          column += (char.ord > 0xFFFF) ? 2 : 1
         end
-        return column + 1 if units >= offset
-        units += (char.ord > 0xFFFF) ? 2 : 1
-        column += 1
       end
-      column + 1
+      [line, column]
     end
 
     DEFAULT_PORT = 8181
@@ -82,29 +66,45 @@ module SimpleEnglish
     def parse_matches(matches, payload)
       payload = to_payload(payload)
       matches.map do |match|
-        line, column = payload.locate(match.fetch("offset"))
+        offset = match.fetch("offset")
+        line, column = payload.locate(offset)
+        end_line, end_column = payload.locate(offset + match.fetch("length"))
         Finding.new(line: line, column: column,
+          end_line: end_line, end_column: end_column,
           rule: match.fetch("rule").fetch("id"),
           message: with_context(match.fetch("message"), match))
       end
     end
 
     # Prefix the offending text, so a finding says what to change,
-    # not only how. LanguageTool returns it in the match context.
-    # Context offsets are Java UTF-16 code units, like the match
-    # offset.
+    # not only how. Context positions use Java UTF-16 code units.
     def with_context(message, match)
       context = match["context"] or return message
-      matched = context.fetch("text", "")[
-        context.fetch("offset", 0).to_i, context.fetch("length", 0).to_i]
+      matched = utf16_slice(context.fetch("text", ""),
+        context.fetch("offset", 0).to_i, context.fetch("length", 0).to_i)
       matched.empty? ? message : "\"#{matched}\" - #{message}"
     end
 
+    def utf16_slice(text, offset, length)
+      first = utf16_index(text, offset)
+      last = utf16_index(text, offset + length)
+      text[first...last]
+    end
+
+    def utf16_index(text, offset)
+      units = 0
+      text.each_char.with_index do |char, index|
+        return index if units >= offset
+        units += (char.ord > 0xFFFF) ? 2 : 1
+      end
+      text.length
+    end
+
     def to_payload(payload)
       payload.is_a?(String) ? PlainText.new(payload) : payload
     end
 
-    private_class_method :to_payload, :with_context
+    private_class_method :to_payload, :with_context, :utf16_slice, :utf16_index
 
     # Full lint via the se daemon. Raw Markdown in, or code
     # source with a language for the comment pipeline. nil when
@@ -119,6 +119,7 @@ module SimpleEnglish
       return nil unless body.is_a?(Array)
       body.map do |hash|
         Finding.new(line: hash.fetch("line"), column: hash["column"],
+          end_line: hash["end_line"], end_column: hash["end_column"],
           rule: hash.fetch("rule"), message: hash.fetch("message"))
       end
     rescue SystemCallError, SocketError, Timeout::Error,

data/lib/simple_english/extractor.rb

@@ -20,7 +20,12 @@ module SimpleEnglish
       ".java" => "java",
       ".sh" => "bash",
       ".kt" => "kotlin",
-      ".cs" => "csharp"
+      ".cs" => "csharp",
+      ".cpp" => "cpp",
+      ".cc" => "cpp",
+      ".cxx" => "cpp",
+      ".hpp" => "cpp",
+      ".h" => "cpp"
     }.freeze
 
     module_function

data/lib/simple_english/finding.rb

@@ -1,8 +1,9 @@
 # frozen_string_literal: true
 
-# One lint result. The line and column are 1-based. The column is
-# nil when the rule has no position within the line.
+# One lint result. Positions are 1-based. The end position is exclusive.
+# Counting findings have no columns or end positions. Findings from an older
+# daemon can have a start column without an end position.
 
 module SimpleEnglish
-  Finding = Struct.new(:line, :column, :rule, :message)
+  Finding = Struct.new(:line, :column, :end_line, :end_column, :rule, :message)
 end

data/lib/simple_english/markdown.rb

@@ -21,21 +21,39 @@ module SimpleEnglish
     module_function
 
     # Blank out code and other non-prose blocks and neutralize inline
-    # code and heading markers. The line count stays identical to the
-    # source.
+    # code and heading markers. Line count and UTF-16 widths stay identical
+    # to the source so LanguageTool offsets remain source positions.
     def strip(text)
-      lines = text.lines.map(&:chomp)
-      blank_rows(text).each { |row| lines[row] = "" }
-      lines.map { |line| strip_line(line) }.join("\n")
+      blank = blank_rows(text).to_h { |row| [row, true] }
+      text.lines.each_with_index.map do |line, row|
+        ending = if line.end_with?("\r\n")
+          "\r\n"
+        elsif line.end_with?("\n")
+          "\n"
+        else
+          ""
+        end
+        body = line.delete_suffix(ending)
+        (blank[row] ? spaces_for(body) : strip_line(body)) + ending
+      end.join
     end
 
     def strip_line(line)
-      # Width-preserving replacements, so a finding column points at
-      # the source line, not at the stripped copy.
-      line.gsub(/`[^`]*`/) { |code| "X" * code.length }
+      # Width-preserving replacements keep LanguageTool positions aligned
+      # with the source.
+      line
+        .gsub(/`[^`]*`/) { |code| "X" * utf16_length(code) }
         .sub(/\A\#{1,6} /) { |marker| " " * marker.length }
     end
 
+    def spaces_for(text)
+      " " * utf16_length(text)
+    end
+
+    def utf16_length(text)
+      text.each_char.sum { |char| (char.ord > 0xFFFF) ? 2 : 1 }
+    end
+
     # A vertical list is not one paragraph: each list item is its own.
     # Paragraph boundaries come from the tree-sitter Markdown grammar,
     # so lazy continuations and interrupted lists match the spec
@@ -97,7 +115,7 @@ module SimpleEnglish
       TreeSitterLanguagePack.get_parser("markdown").parse(text).root_node
     end
 
-    private_class_method :strip_line, :node_rows, :blank_rows, :each_node,
-      :inside_list_item?, :parse
+    private_class_method :strip_line, :spaces_for, :utf16_length, :node_rows,
+      :blank_rows, :each_node, :inside_list_item?, :parse
   end
 end

data/lib/simple_english/plain_text.rb

@@ -10,8 +10,7 @@ module SimpleEnglish
       end
 
       def locate(utf16_offset)
-        [Client.offset_to_line(text, utf16_offset),
-          Client.offset_to_column(text, utf16_offset)]
+        Client.offset_to_position(text, utf16_offset)
       end
     end
   end

data/lib/simple_english/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SimpleEnglish
-  VERSION = "0.2.0"
+  VERSION = "0.3.0"
 end

data/rules/simple-english.xml

@@ -56,10 +56,14 @@
     </rule>
 
     <rule id="SE_ING_AFTER_COMMA" name="No -ing after a comma">
-      <pattern><token>,</token><token postag="VBG"/></pattern>
+      <pattern><token>,</token><token postag="VBG"><exception scope="next" regexp="yes">[,)]|and|or</exception></token></pattern>
       <message>Start a new sentence instead of the -ing phrase.</message>
       <example type="incorrect">The tool runs<marker>, making</marker> it easy.</example>
       <example type="correct">The tool runs. It is easy.</example>
+      <example type="correct">The walkthrough (accounts, VPC, secrets, troubleshooting) is in the guide.</example>
+      <example type="correct">The guide covers billing, troubleshooting, and support for each environment.</example>
+      <example type="correct">The guide covers billing, troubleshooting and support for each environment.</example>
+      <example type="correct">The guide covers billing, troubleshooting or support for each environment.</example>
     </rule>
 
     <rule id="SE_KEEP_THAT" name="make sure that">

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_english
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.3.0
 platform: ruby
 authors:
 - TonyCTHsu
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-09-28 00:00:00.000000000 Z
+date: 2026-09-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: tree_sitter_language_pack
@@ -159,7 +159,10 @@ files:
 homepage: https://github.com/TonyCTHsu/simple-english
 licenses:
 - MIT
-metadata: {}
+metadata:
+  homepage_uri: https://github.com/TonyCTHsu/simple-english
+  source_code_uri: https://github.com/TonyCTHsu/simple-english
+  changelog_uri: https://github.com/TonyCTHsu/simple-english/blob/v0.3.0/CHANGELOG.md
 post_install_message:
 rdoc_options: []
 require_paths: