sync upstream

.github/workflows/build.yml

@@ -0,0 +1,34 @@
+name: 🏗️ Build
+
+on:
+  push:
+    branches: [main]
+  pull_request: ~
+
+env:
+  GO_VERSION: "1.25"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Set up Go ${{ env.GO_VERSION }}
+        uses: actions/setup-go@v6
+        with:
+          go-version: ${{ env.GO_VERSION }}
+
+      - name: 📦 Install Mise
+        run: |
+          curl https://mise.run | sh
+          mise install
+
+      - name: Install dependencies
+        run: sudo apt install wv unrtf tidy
+
+      - name: Build
+        run: mise build
+
+      - name: Test
+        run: mise test

.github/workflows/release.yml

@@ -0,0 +1,31 @@
+name: 🚀 Publish Release
+
+on:
+  push:
+    tags:
+      - 'v?[0-9]+.[0-9]+.[0-9]+(-alpha[0-9]+|-beta[0-9]+)?'
+
+env:
+  GO_VERSION: "1.25"
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: 📦 Install Mise
+        run: |
+          curl https://mise.run | sh
+          mise install
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Run GoReleaser Snapshot
+        run: mise release
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/snapshot.yml

@@ -0,0 +1,34 @@
+name: 👨‍🔧 Build Snapshot Release
+
+on:
+  workflow_dispatch: ~
+
+env:
+  GO_VERSION: "1.25"
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Set up Go
+        uses: actions/setup-go@v6
+        with:
+          go-version: ${{ env.GO_VERSION }}
+
+      - name: 📦 Install Mise
+        run: |
+          curl https://mise.run | sh
+          mise install
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Run GoReleaser Snapshot
+        run: mise snapshot
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -1,3 +1,5 @@
 
 sajari-convert
 *tests/
+/dist
+/vendor

.goreleaser.yml

@@ -0,0 +1,50 @@
+project_name: docconv
+
+version: 2
+
+builds:
+  - id: docconv-build
+    main: ./docd
+    binary: docconv
+    ldflags:
+      - -extldflags '-static'
+    env:
+      - CGO_ENABLED=0
+    goos: [ linux ]
+    goarch: [ amd64, arm64 ]
+
+release:
+  prerelease: auto
+  name_template: "docconv {{.Version}}"
+  github:
+    owner: skpr
+    name: docconv
+
+nfpms:
+  - id: docconv-package
+    package_name: docconv
+    license: MIT
+    maintainer: Skpr
+    homepage: https://github.com/skpr/docconv
+    description: Fork of https://github.com/sajari/docconv to add additional package formats.
+    formats: [ apk ]
+    dependencies:
+      - tesseract-ocr
+      - poppler-utils
+    overrides:
+      apk:
+        dependencies:
+          - tesseract-ocr
+          - tesseract-ocr-dev
+          - poppler-utils
+
+dockers_v2:
+  - images:
+      - "docker.io/skpr/docconv"
+      - "ghcr.io/skpr/docconv"
+    tags:
+      - "{{ .Version }}"
+      - "latest"
+    platforms:
+      - linux/amd64
+      - linux/arm64

.mise.toml

@@ -0,0 +1,25 @@
+[tools]
+go = "1.25"
+"ubi:goreleaser/goreleaser" = "latest"
+
+[env]
+CGO_ENABLED=0
+LGFLAGS="-extldflags '-static'"
+
+[tasks.build]
+description = "Build the application"
+run = '''
+go build -v -o ./dist/docconv ./docd
+'''
+
+[tasks.test]
+description = "Run tests"
+run = "go test -v ./..."
+
+[tasks.snapshot]
+description = "Create a snapshot release with Goreleaser"
+run = "goreleaser release --snapshot --clean"
+
+[tasks.release]
+description = "Create a release with Goreleaser"
+run = "goreleaser release --clean"

Dockerfile

@@ -0,0 +1,8 @@
+ARG ALPINE_VERSION=3.21
+FROM alpine:$ALPINE_VERSION
+
+RUN apk add --no-cache tesseract-ocr tesseract-ocr-dev poppler-utils
+
+ARG TARGETPLATFORM
+COPY $TARGETPLATFORM/docconv /usr/bin/docconv
+ENTRYPOINT ["/usr/bin/docconv"]

README.md

@@ -1,42 +1,69 @@
 # docconv
 
-[![GoDoc](https://godoc.org/code.sajari.com/docconv?status.svg)](https://godoc.org/code.sajari.com/docconv)
-[![Build Status](https://travis-ci.org/sajari/docconv.svg?branch=master)](https://travis-ci.org/sajari/docconv)
+[![Go reference](https://pkg.go.dev/badge/code.sajari.com/docconv/v2.svg)](https://pkg.go.dev/code.sajari.com/docconv/v2)
+[![Build status](https://github.com/sajari/docconv/workflows/Go/badge.svg?branch=master)](https://github.com/sajari/docconv/actions)
+[![Report card](https://goreportcard.com/badge/code.sajari.com/docconv/v2)](https://goreportcard.com/report/code.sajari.com/docconv/v2)
+[![Sourcegraph](https://sourcegraph.com/github.com/sajari/docconv/v2/-/badge.svg)](https://sourcegraph.com/github.com/sajari/docconv/v2)
 
 A Go wrapper library to convert PDF, DOC, DOCX, XML, HTML, RTF, ODT, Pages documents and images (see optional dependencies below) to plain text.
 
-> **Note for returning users:** the Go import path for this package been moved to `code.sajari.com/docconv`.
-
 ## Installation
 
 If you haven't setup Go before, you first need to [install Go](https://golang.org/doc/install).
 
 To fetch and build the code:
 
-    $ go get code.sajari.com/docconv/...
+```console
+$ go install code.sajari.com/docconv/v2/docd@latest
+```
+
+See `go help install` for details on the installation location of the installed `docd` executable. Make sure that the full path to the executable is in your `PATH` environment variable.
 
-This will also build the command line tool `docd` into `$GOPATH/bin`. Make sure that `$GOPATH/bin` is in your `PATH` environment variable.
+## Build
+
+```
+docker run -it -v $(pwd):/go/src/github.com/skpr/docconv -w /go/src/github.com/skpr/docconv golang:1.23-alpine3.11 /bin/sh -c "./build.sh 3.11"
+docker run -it -v $(pwd):/go/src/github.com/skpr/docconv -w /go/src/github.com/skpr/docconv golang:1.23-alpine3.12 /bin/sh -c "./build.sh 3.12"
+docker run -it -v $(pwd):/go/src/github.com/skpr/docconv -w /go/src/github.com/skpr/docconv golang:1.23-alpine3.13 /bin/sh -c "./build.sh 3.13"
+```
 
 ## Dependencies
 
-tidy, wv, popplerutils, unrtf, https://github.com/JalfResi/justext
+- tidy
+- wv
+- popplerutils
+- unrtf
+- https://github.com/JalfResi/justext
+
+### Debian-based Linux
 
-Example install of dependencies (not all systems):
+```console
+$ sudo apt-get install poppler-utils wv unrtf tidy
+$ go get github.com/JalfResi/justext
+```
 
-    $ sudo apt-get install poppler-utils wv unrtf tidy
-    $ go get github.com/JalfResi/justext
+### macOS
+
+```console
+$ brew install poppler-qt5 wv unrtf tidy-html5
+$ go get github.com/JalfResi/justext
+```
 
 ### Optional dependencies
 
 To add image support to the `docconv` library you first need to [install and build gosseract](https://github.com/otiai10/gosseract/tree/v2.2.4).
 
 Now you can add `-tags ocr` to any `go` command when building/fetching/testing `docconv` to include support for processing images:
 
-    $ go get -tags ocr code.sajari.com/docconv/...
+```console
+$ go get -tags ocr code.sajari.com/docconv/v2/...
+```
 
 This may complain on macOS, which you can fix by installing [tesseract](https://tesseract-ocr.github.io) via brew:
 
-    $ brew install tesseract
+```console
+$ brew install tesseract
+```
 
 ## docd tool
 
@@ -48,27 +75,27 @@ The `docd` tool runs as either:
 
 2.  a service exposed from within a Docker container
 
-    This also runs as a service, but from within a Docker container. There are three build scripts:
+    This also runs as a service, but from within a Docker container.
+    Official images are published at https://hub.docker.com/r/sajari/docd.
 
-    - [./docd/debian.sh](./docd/debian.sh)
-    - [./docd/alpine.sh](./docd/alpine.sh)
-    - [./docd/appengine.sh](./docd/appengine.sh)
+    Optionally you can build it yourself:
 
-    The `debian` version uses the Debian package repository which can vary with builds. The `alpine` version uses a very cut down Linux distribution to produce a container ~40MB. It also locks the dependency versions for consistency, but may miss out on future updates. The `appengine` version is a flex based custom runtime for Google Cloud.
+    ```console
+    $ cd docd
+    $ docker build -t docd .
+    ```
 
 3.  via the command line.
 
     Documents can be sent as an argument, e.g.
 
-        $ docd -input document.pdf
+    ```console
+    $ docd -input document.pdf
+    ```
 
 ### Optional flags
 
 - `addr` - the bind address for the HTTP server, default is ":8888"
-- `log-level`
-  - 0: errors & critical info
-  - 1: inclues 0 and logs each request as well
-  - 2: include 1 and logs the response payloads
 - `readability-length-low` - sets the readability length low if the ?readability=1 parameter is set
 - `readability-length-high` - sets the readability length high if the ?readability=1 parameter is set
 - `readability-stopwords-low` - sets the readability stopwords low if the ?readability=1 parameter is set
@@ -79,11 +106,10 @@ The `docd` tool runs as either:
 
 ### How to start the service
 
-    $ # This will only log errors and critical info
-    $ docd -log-level 0
-
-    $ # This will run on port 8000 and log each request
-    $ docd -addr :8000 -log-level 1
+```console
+$ # This runs on port 8000
+$ docd -addr :8000
+```
 
 ## Example usage (code)
 
@@ -100,15 +126,14 @@ package main
 
 import (
 	"fmt"
-	"log"
 
-	"code.sajari.com/docconv"
+	"code.sajari.com/docconv/v2"
 )
 
 func main() {
 	res, err := docconv.ConvertPath("your-file.pdf")
 	if err != nil {
-		log.Fatal(err)
+		// TODO: handle
 	}
 	fmt.Println(res)
 }
@@ -121,9 +146,8 @@ package main
 
 import (
 	"fmt"
-	"log"
 
-	"code.sajari.com/docconv/client"
+	"code.sajari.com/docconv/v2/client"
 )
 
 func main() {
@@ -132,8 +156,14 @@ func main() {
 
 	res, err := client.ConvertPath(c, "your-file.pdf")
 	if err != nil {
-		log.Fatal(err)
+		// TODO: handle
 	}
 	fmt.Println(res)
 }
 ```
+
+Alternatively, via a `curl`:
+
+```console
+$ curl -s -F input=@your-file.pdf http://localhost:8888/convert
+```

build.sh

@@ -0,0 +1,6 @@
+#!/bin/sh
+
+VERSION=$1
+
+apk add make cmake gcc g++ poppler-utils wv lynx tesseract-ocr-dev
+go build -o dist/docconv-${VERSION} -tags ocr github.com/skpr/docconv/docd