tesseract: add new image (#2469)

Signed-off-by: Dimitri John Ledkov <[email protected]>

images/tesseract/README.md

@@ -0,0 +1,40 @@
+<!--monopod:start-->
+# tesseract
+| | |
+| - | - |
+| **OCI Reference** | `cgr.dev/chainguard/tesseract` |
+
+
+* [View Image in Chainguard Academy](https://edu.chainguard.dev/chainguard/chainguard-images/reference/tesseract/overview/)
+* [View Image Catalog](https://console.enforce.dev/images/catalog) for a full list of available tags.
+* [Contact Chainguard](https://www.chainguard.dev/chainguard-images) for enterprise support, SLAs, and access to older tags.*
+
+---
+<!--monopod:end-->
+
+<!--overview:start-->
+Minimal image that contains tesseract
+<!--overview:end-->
+
+<!--getting:start-->
+## Download this Image
+The image is available on `cgr.dev`:
+
+```
+docker pull cgr.dev/chainguard/tesseract:latest
+```
+<!--getting:end-->
+
+<!--body:start-->
+# Usage
+
+tessaract sample Example: OCR a eurotext.png file to .txt
+
+```
+docker run --rm \
+    -v "${PWD}":/work \
+    -w /work \
+    cgr.dev/chainguard/tesseract:latest
+    eurotext.png -
+```
+<!--body:end-->

images/tesseract/config/main.tf

@@ -0,0 +1,20 @@
+terraform {
+  required_providers {
+    apko = { source = "chainguard-dev/apko" }
+  }
+}
+
+variable "extra_packages" {
+  description = "The additional packages to install"
+  # Install tesseract itself, orientation & size & english datasets
+  default = ["tesseract", "tesseract-osd", "tesseract-eng"]
+}
+
+data "apko_config" "this" {
+  config_contents = file("${path.module}/template.apko.yaml")
+  extra_packages  = var.extra_packages
+}
+
+output "config" {
+  value = jsonencode(data.apko_config.this.config)
+}

images/tesseract/config/template.apko.yaml

@@ -0,0 +1,14 @@
+accounts:
+  groups:
+    - groupname: nonroot
+      gid: 65532
+  users:
+    - username: nonroot
+      uid: 65532
+      gid: 65532
+  run-as: 65532
+
+entrypoint:
+  command: /usr/bin/tesseract
+
+cmd: --help

images/tesseract/main.tf

@@ -0,0 +1,38 @@
+terraform {
+  required_providers {
+    oci = { source = "chainguard-dev/oci" }
+  }
+}
+
+variable "target_repository" {
+  description = "The docker repo into which the image and attestations should be published."
+}
+
+module "latest-config" { source = "./config" }
+
+module "latest" {
+  source = "../../tflib/publisher"
+
+  name = basename(path.module)
+
+  target_repository = var.target_repository
+  config            = module.latest-config.config
+  build-dev         = true
+}
+
+module "test-latest" {
+  source = "./tests"
+  digest = module.latest.image_ref
+}
+
+resource "oci_tag" "latest" {
+  depends_on = [module.test-latest]
+  digest_ref = module.latest.image_ref
+  tag        = "latest"
+}
+
+resource "oci_tag" "latest-dev" {
+  depends_on = [module.test-latest]
+  digest_ref = module.latest.dev_ref
+  tag        = "latest-dev"
+}

images/tesseract/metadata.yaml

@@ -0,0 +1,11 @@
+name: tesseract
+image: cgr.dev/chainguard/tesseract
+endoflife: ""
+console_summary: ""
+short_description: Minimal image that contains tesseract
+compatibility_notes: ""
+readme_file: README.md
+upstream_url: https://tesseract-ocr.github.io/
+keywords:
+  - application
+  - tools

images/tesseract/tests/.gitignore

@@ -0,0 +1 @@
+eurotext.txt

images/tesseract/tests/01-eurotext-ocr.sh

@@ -0,0 +1,12 @@
+#!/usr/bin/env bash
+
+## Using example image from
+## https://tesseract-ocr.github.io/tessdoc/images/eurotext.png
+
+set -o errexit -o nounset -o errtrace -o pipefail -x
+
+docker run --rm \
+    -v "${PWD}:/work" \
+    -w /work \
+    "${IMAGE_NAME}" \
+    eurotext.png - | diff -u eurotext.exp -

images/tesseract/tests/eurotext.exp

@@ -0,0 +1,12 @@
+The (quick) [brown] {fox} jumps!
+Over the $43,456.78 <lazy> #90 dog
+& duck/goose, as 12.5% of E-mail
+from [email protected] is spam.
+Der ,schnelle” braune Fuchs springt
+iiber den faulen Hund. Le renard brun
+«rapide» saute par-dessus le chien
+paresseux. La volpe marrone rapida
+salta sopra il cane pigro. El zorro
+marrén rapido salta sobre el perro
+perezoso. A raposa marrom ripida
+salta sobre o cdo preguigoso.

images/tesseract/tests/main.tf

@@ -0,0 +1,20 @@
+terraform {
+  required_providers {
+    oci = { source = "chainguard-dev/oci" }
+  }
+}
+
+variable "digest" {
+  description = "The image digest to run tests over."
+}
+
+data "oci_exec_test" "help" {
+  digest = var.digest
+  script = "docker run --rm $IMAGE_NAME --help"
+}
+
+data "oci_exec_test" "convert" {
+  digest      = var.digest
+  script      = "./01-eurotext-ocr.sh"
+  working_dir = path.module
+}

main.tf

@@ -1441,6 +1441,11 @@ module "terraform" {
   target_repository = "${var.target_repository}/terraform"
 }
 
+module "tesseract" {
+  source            = "./images/tesseract"
+  target_repository = "${var.target_repository}/tesseract"
+}
+
 module "thanos" {
   source            = "./images/thanos"
   target_repository = "${var.target_repository}/thanos"