From b3e0041036e28da130362371c596e9e41a6d274b Mon Sep 17 00:00:00 2001
From: tannevaled <tannevaled@users.noreply.github.com>
Date: Mon, 12 Oct 2026 10:09:10 +0200
Subject: [PATCH] A card for document, the tables extract now finds, and
 landingkit v0.3.1

go-pdfkit/document is a new repository and the landing did not know it existed.
Its card says what the inference IS -- a heading is text set larger than the
body AND rare with it -- and what it will not read: ruled lines, multi-column
layouts, footnotes.

extract's card gained the tables, with the number that matters: on one
213-page document three rules took the count from 588 to 40, which are the
real ones, and a prose report in the same run reports none.

ops's card listed 23 verbs by name and there are 49. The list now names the
ones somebody would look for and says the count, rather than reading as a
complete list that is not one.

landingkit v0.3.0 -> v0.3.1, whose `verify` finds [params.brand] at the start
of a line rather than inside a comment that names it -- and this hugo.toml has
exactly such a comment, so the check was reading the wrong thing here.

Verified against the reference, go-fileshare.github.io:

  PASS the <style> block equals the reference's once brand values are masked
  PASS light: 62/62 background pixels identical (#ffffff)
  PASS dark: 62/62 background pixels identical (#0b0e14)

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
---
 go.mod    |  2 +-
 go.sum    |  2 ++
 hugo.toml | 11 +++++++++--
 3 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/go.mod b/go.mod
index 93b0f20..3606723 100644
--- a/go.mod
+++ b/go.mod
@@ -2,4 +2,4 @@ module github.com/go-pdfkit/go-pdfkit.github.io
 
 go 1.27.1
 
-require github.com/go-fleettools/landingkit v0.3.0
+require github.com/go-fleettools/landingkit v0.3.1
diff --git a/go.sum b/go.sum
index 83ad761..c842a3e 100644
--- a/go.sum
+++ b/go.sum
@@ -1,2 +1,4 @@
 github.com/go-fleettools/landingkit v0.3.0 h1:vFzTuAYjuTQUJ80B8T87JyIxATZ4wof+3adwcfrST6U=
 github.com/go-fleettools/landingkit v0.3.0/go.mod h1:NUBMh7cVFUfD/hX6Xv5ef2O/r4F6rPtPGGVd3T+9qc0=
+github.com/go-fleettools/landingkit v0.3.1 h1:vW/xVaXYKF+XXgFFQAqBKhSWV6hpCkvsAZ3t1MdWPnc=
+github.com/go-fleettools/landingkit v0.3.1/go.mod h1:NUBMh7cVFUfD/hX6Xv5ef2O/r4F6rPtPGGVd3T+9qc0=
diff --git a/hugo.toml b/hugo.toml
index a1711f6..daac5e5 100644
--- a/hugo.toml
+++ b/hugo.toml
@@ -60,7 +60,7 @@ disableKinds = ["taxonomy", "term", "RSS", "sitemap", "404"]
   pkg = "github.com/go-pdfkit/ops"
   url = "https://github.com/go-pdfkit/ops"
   status = "ready"
-  blurb = "**The verbs, and the `pdfops` command.** Merge, select, delete, reverse, move, rotate, crop, resize, split, n-up, booklet, overlay, blank pages, watermarks, page numbers, Bates stamps, sanitize, flatten, compress, encrypt, decrypt, permissions, and reading a page back as text or pictures. Links and bookmarks are carried over and pointed at the pages they became. Every verb is measured on the whole corpus: 118 833 files compressed and read back **page for page identical**, 35.2 GB down to 33.6 GB."
+  blurb = "**The verbs, and the `pdfops` command** — 49 of them. Merge, select, delete, reverse, move, rotate, crop, resize, split, n-up, booklet, poster, divide, duplex, overlay, blank pages, watermarks, page numbers, Bates stamps, page labels, layers, text colour, sanitize, flatten, compress, encrypt, decrypt, permissions, repair, attachments, forms — and reading a page back as text, pictures, **tables** (CSV, JSON or Markdown) or a whole **document** in Markdown. Links and bookmarks are carried over and pointed at the pages they became. Every verb is measured on the whole corpus: 118 833 files compressed and read back **page for page identical**, 35.2 GB down to 33.6 GB."
 
 [[params.repos]]
   name = "render"
@@ -88,7 +88,14 @@ disableKinds = ["taxonomy", "term", "RSS", "sitemap", "404"]
   pkg = "github.com/go-pdfkit/extract"
   url = "https://github.com/go-pdfkit/extract"
   status = "ready"
-  blurb = "**Reads a page back**: the text with where each piece of it sits, and the pictures with the box each covers. A page holds instructions for drawing glyphs, not text — so where the document says nothing about what they mean, this **says so** rather than guessing. Over the whole corpus: 121 946 pages, 34 million characters, 1.89% of runs that nothing in the document could name, 300 685 pictures located, no panics."
+  blurb = "**Reads a page back**: the text with where each piece of it sits, the pictures with the box each covers, and the **grids its text lines up into**. A page holds instructions for drawing glyphs, not text — so where the document says nothing about what they mean, this **says so** rather than guessing. A column boundary is a stretch of page every row leaves empty, and three things that look like columns are not: a bullet, a column nothing was drawn in, and a page number. On one 213-page document those three took the count from 588 tables to **40**, which are the real ones; a prose report in the same run reports none. Over the whole corpus: 121 946 pages, 34 million characters, 1.89% of runs that nothing in the document could name, 300 685 pictures located, no panics."
+
+[[params.repos]]
+  name = "document"
+  pkg = "github.com/go-pdfkit/document"
+  url = "https://github.com/go-pdfkit/document"
+  status = "ready"
+  blurb = "**A PDF read back as a document rather than as text** — headings, paragraphs, lists and tables, into the [richdoc](https://github.com/go-richdoc/richdoc) model, which gets Markdown, reST and HTML out of a PDF through code the fleet already has. A page has no headings: it has glyphs at places, and everything above that is an **inference**. A heading is text set larger than the body *and* rare with it — measured over six real documents, heading sizes hold 0.01% to 5.76% of the characters and a second body size holds a third, and taking \"larger\" alone gave a nine-page report 131 headings of which 130 were prose. What it will not read is published too: ruled lines, columns of a multi-column layout, and footnotes."
 
 [[params.repos]]
   name = "coedit"