octo-agent 0.11.2

data/lib/octo/default_parsers/pdf_parser_plumber.py

@@ -0,0 +1,62 @@
+#!/usr/bin/env python3
+"""
+pdf_parser_plumber.py — extract text from a PDF using pdfplumber.
+
+Usage:
+    python3 pdf_parser_plumber.py <file_path>
+
+Output:
+    stdout — extracted text, one block per page, separated by blank lines
+    stderr — error messages
+    exit 0  — success (text was extracted)
+    exit 1  — failure / no text found
+    exit 2  — dependency missing
+
+Called from pdf_parser.rb as the second-tier extractor (after pdftotext).
+This script is copied into ~/.octo/parsers/ and can be edited freely by
+the LLM — e.g. to tune table extraction, layout heuristics, or filter out
+boilerplate headers/footers. Edit, then re-run to test.
+
+Install:
+    pip3 install pdfplumber
+"""
+
+# VERSION: 1
+
+import sys
+
+
+def main():
+    if len(sys.argv) < 2:
+        sys.stderr.write("Usage: pdf_parser_plumber.py <file_path>\n")
+        sys.exit(1)
+
+    path = sys.argv[1]
+
+    try:
+        import pdfplumber
+    except ImportError as e:
+        sys.stderr.write(f"pdfplumber missing: {e}\n")
+        sys.stderr.write("Install with: pip3 install pdfplumber\n")
+        sys.exit(2)
+
+    pages = []
+    try:
+        with pdfplumber.open(path) as pdf:
+            for i, page in enumerate(pdf.pages, 1):
+                text = page.extract_text()
+                if text and text.strip():
+                    pages.append(f"--- Page {i} ---\n{text.strip()}")
+    except Exception as e:
+        sys.stderr.write(f"pdfplumber failed: {e}\n")
+        sys.exit(1)
+
+    if not pages:
+        sys.stderr.write("pdfplumber produced no text.\n")
+        sys.exit(1)
+
+    print("\n\n".join(pages))
+
+
+if __name__ == "__main__":
+    main()

data/lib/octo/default_parsers/pptx_parser.rb

@@ -0,0 +1,140 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+#
+# Octo PPTX Parser — CLI interface
+#
+# Usage:
+#   ruby pptx_parser.rb <file_path>
+#
+# Output:
+#   stdout — extracted content in Markdown (UTF-8)
+#   stderr — error messages
+#   exit 0 — success
+#   exit 1 — failure
+#
+# Dependencies: rubyzip gem (gem install rubyzip)
+#
+# This file lives in ~/.octo/parsers/ and can be modified by the LLM.
+#
+# VERSION: 1
+
+require "zip"
+require "rexml/document"
+require "stringio"
+
+def extract_text(shape_node)
+  paras = []
+  REXML::XPath.each(shape_node, ".//a:p") do |para|
+    text = REXML::XPath.match(para, ".//a:t").map(&:text).compact.join
+    paras << text unless text.strip.empty?
+  end
+  paras.join("\n")
+end
+
+def parse_table(tbl_node)
+  rows = []
+  REXML::XPath.each(tbl_node, ".//a:tr") do |tr|
+    cells = REXML::XPath.match(tr, ".//a:tc").map do |tc|
+      REXML::XPath.match(tc, ".//a:t").map(&:text).compact.join(" ").strip
+    end
+    rows << cells
+  end
+  return "" if rows.empty?
+
+  col_count = rows.map(&:size).max
+  lines = []
+  rows.each_with_index do |row, i|
+    padded = row + [""] * [col_count - row.size, 0].max
+    lines << "| #{padded.join(" | ")} |"
+    lines << "|#{" --- |" * col_count}" if i == 0
+  end
+  lines.join("\n")
+end
+
+def parse_slide(doc, slide_num)
+  lines = []
+
+  title_text = nil
+  REXML::XPath.each(doc, "//p:sp") do |sp|
+    ph = REXML::XPath.first(sp, ".//p:ph")
+    next unless ph
+    ph_type = ph.attributes["type"]
+    if ph_type == "title" || ph_type == "ctrTitle"
+      title_text = extract_text(sp).strip
+      break
+    end
+  end
+
+  lines << "## Slide #{slide_num}#{title_text && !title_text.empty? ? ": #{title_text}" : ""}"
+
+  REXML::XPath.each(doc, "//p:sp") do |sp|
+    ph = REXML::XPath.first(sp, ".//p:ph")
+    if ph
+      ph_type = ph.attributes["type"]
+      next if %w[title ctrTitle sldNum dt ftr].include?(ph_type)
+    end
+
+    text = extract_text(sp).strip
+    next if text.empty?
+    next if text == title_text
+
+    text.each_line do |line|
+      lines << "- #{line.rstrip}" unless line.strip.empty?
+    end
+  end
+
+  REXML::XPath.each(doc, "//a:tbl") do |tbl|
+    lines << parse_table(tbl)
+  end
+
+  lines.join("\n")
+end
+
+# --- main ---
+
+path = ARGV[0]
+
+if path.nil? || path.empty?
+  warn "Usage: ruby pptx_parser.rb <file_path>"
+  exit 1
+end
+
+unless File.exist?(path)
+  warn "File not found: #{path}"
+  exit 1
+end
+
+begin
+  body   = File.binread(path)
+  slides = {}
+
+  Zip::File.open_buffer(StringIO.new(body)) do |zip|
+    zip.each do |entry|
+      if entry.name =~ %r{ppt/slides/slide(\d+)\.xml}
+        slides[$1.to_i] = entry.get_input_stream.read
+      end
+    end
+  end
+
+  if slides.empty?
+    warn "Presentation appears to be empty"
+    exit 1
+  end
+
+  sections = slides.keys.sort.map do |num|
+    doc = REXML::Document.new(slides[num])
+    parse_slide(doc, num)
+  end.compact
+
+  if sections.empty?
+    warn "Presentation appears to be empty"
+    exit 1
+  end
+
+  print sections.join("\n\n---\n\n")
+  exit 0
+rescue => e
+  warn "Failed to parse PPTX: #{e.message}"
+  warn "Tip: ensure rubyzip is installed: gem install rubyzip"
+  exit 1
+end

data/lib/octo/default_parsers/xlsx_parser.rb

@@ -0,0 +1,121 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+#
+# Octo XLSX Parser — CLI interface
+#
+# Usage:
+#   ruby xlsx_parser.rb <file_path>
+#
+# Output:
+#   stdout — extracted content in Markdown tables (UTF-8)
+#   stderr — error messages
+#   exit 0 — success
+#   exit 1 — failure
+#
+# Dependencies: rubyzip gem (gem install rubyzip)
+#
+# This file lives in ~/.octo/parsers/ and can be modified by the LLM.
+#
+# VERSION: 1
+
+require "zip"
+require "rexml/document"
+require "stringio"
+
+def parse_row(row_node, shared_strings)
+  REXML::XPath.match(row_node, ".//c").map do |c|
+    v = REXML::XPath.first(c, "v")&.text
+    next "" unless v
+    c.attributes["t"] == "s" ? (shared_strings[v.to_i] || "") : v
+  end
+end
+
+def build_markdown_table(rows)
+  col_count = rows.map(&:size).max
+  lines = []
+  rows.each_with_index do |row, i|
+    padded = row + [""] * [col_count - row.size, 0].max
+    lines << "| #{padded.join(" | ")} |"
+    lines << "|#{" --- |" * col_count}" if i == 0
+  end
+  lines.join("\n")
+end
+
+# --- main ---
+
+path = ARGV[0]
+
+if path.nil? || path.empty?
+  warn "Usage: ruby xlsx_parser.rb <file_path>"
+  exit 1
+end
+
+unless File.exist?(path)
+  warn "File not found: #{path}"
+  exit 1
+end
+
+begin
+  body = File.binread(path)
+  shared_strings = []
+  sheet_names    = {}
+  sheet_xmls     = {}
+
+  Zip::File.open_buffer(StringIO.new(body)) do |zip|
+    ss_entry = zip.find_entry("xl/sharedStrings.xml")
+    if ss_entry
+      doc = REXML::Document.new(ss_entry.get_input_stream.read)
+      REXML::XPath.each(doc, "//si") do |si|
+        shared_strings << REXML::XPath.match(si, ".//t").map(&:text).compact.join
+      end
+    end
+
+    wb_entry = zip.find_entry("xl/workbook.xml")
+    if wb_entry
+      doc = REXML::Document.new(wb_entry.get_input_stream.read)
+      REXML::XPath.each(doc, "//sheet") do |s|
+        idx  = s.attributes["sheetId"]
+        name = s.attributes["name"]
+        sheet_names[idx] = name if idx && name
+      end
+    end
+
+    zip.each do |entry|
+      if entry.name =~ %r{xl/worksheets/sheet(\d+)\.xml}
+        sheet_xmls[$1] = entry.get_input_stream.read
+      end
+    end
+  end
+
+  if sheet_xmls.empty?
+    warn "Spreadsheet appears to be empty"
+    exit 1
+  end
+
+  sections = []
+  sheet_xmls.keys.sort_by(&:to_i).each do |idx|
+    name = sheet_names[idx] || "Sheet#{idx}"
+    doc  = REXML::Document.new(sheet_xmls[idx])
+
+    rows = []
+    REXML::XPath.each(doc, "//row") do |row|
+      cells = parse_row(row, shared_strings)
+      rows << cells unless cells.all?(&:empty?)
+    end
+
+    next if rows.empty?
+    sections << "### #{name}\n\n#{build_markdown_table(rows)}"
+  end
+
+  if sections.empty?
+    warn "Spreadsheet appears to be empty"
+    exit 1
+  end
+
+  print sections.join("\n\n")
+  exit 0
+rescue => e
+  warn "Failed to parse XLSX: #{e.message}"
+  warn "Tip: ensure rubyzip is installed: gem install rubyzip"
+  exit 1
+end