Merge pull request #27 from leferrad/release/1.3.2

Release v1.3.2

Author: leferrad

.github/workflows/CI.yml

@@ -47,6 +47,8 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v2
+      - name: Install Tesseract
+        run: sudo apt-get update && sudo apt-get install -y tesseract-ocr
       - uses: julia-actions/setup-julia@v1
         with:
           version: '1'

.github/workflows/CompatHelper.yml

@@ -7,6 +7,8 @@ jobs:
   CompatHelper:
     runs-on: ubuntu-latest
     steps:
+      - name: Install Tesseract
+        run: sudo apt-get update && sudo apt-get install -y tesseract-ocr
       - name: Pkg.add("CompatHelper")
         run: julia -e 'using Pkg; Pkg.add("CompatHelper")'
       - name: CompatHelper.main()

Project.toml

@@ -1,7 +1,7 @@
 name = "OCReract"
 uuid = "c9880795-194d-450c-832d-1e8a03a8ecd1"
 authors = ["Leandro Ferrado"]
-version = "1.3.1"
+version = "1.3.2"
 
 [deps]
 FileIO = "5789e2e9-d7fb-5bc7-8068-2c6fae9b9549"

README.md

@@ -10,11 +10,12 @@
 ## Installation
 
 From the Julia REPL, type `]` to enter the Pkg REPL mode and run:
+
 ```julia-repl
 pkg> add OCReract
 ```
 
-This is just a wrapper, so it assumes you already have installed [Tesseract](https://tesseract-ocr.github.io/tessdoc/Installation.html).
+This is just a wrapper, so it assumes you already have installed [Tesseract](https://tesseract-ocr.github.io/tessdoc/Installation.html). Also, be sure the binary `tesseract` is in your PATH (you can check this by running `tesseract --version` in your terminal).
 
 ## Usage
 
@@ -37,4 +38,5 @@ julia> println(strip(res_text));
 In a Julia session, run `Pkg.test("OCReract", coverage=true)`.
 
 ## Next steps
+
 - Develop a module for image pre-processing (to improve OCR results)

docs/src/index.md

@@ -10,12 +10,13 @@ OCReract is a simple Julia wrapper of the well-known OCR engine called [Tesserac
 The Tesseract OCR engine must be installed manually. On ubuntu, this may be as simple as
 
 ```
-$ sudo apt-get install -y tesseract-ocr
+sudo apt-get install -y tesseract-ocr
 ```
 
 but the [installation instructions](https://tesseract-ocr.github.io/tessdoc/Installation.html) are the authoritative source.
 
 The Julia wrapper can be installed using the Julia package manager. From the Julia REPL, type `]` to enter the Pkg REPL mode and run:
+
 ```julia-repl
 pkg> add OCReract
 ```
@@ -26,7 +27,7 @@ In this simple example, we will process the following image through the two opti
 
 ![Test Image](https://raw.githubusercontent.com/leferrad/OCReract.jl/master/test/files/noisy.png)
 
-#### In disk
+### In disk
 
 Let's execute `run_tesseract` to process the image from repository's test folder, and then `cat` the resulting text file.
 
@@ -39,7 +40,7 @@ julia> read(`cat $res_path`, String)
 "Noisy image\nto test\nOCReract.jl\n\f"
 ```
 
-#### In memory
+### In memory
 
 `OCReract` uses [JuliaImages](https://juliaimages.org/latest/) module to process images in memory. So, the image should be loaded with `Images` module (or the lighter-weight combination `using ImageCore, FileIO`) to then execute `run_tesseract` to retrieve the result as a `String`.
 
@@ -61,6 +62,12 @@ OCReract.jl
 ```@index
 ```
 
+```@docs
+OCReract.OCReract
+OCReract.check_tesseract_installed
+OCReract.get_tesseract_version
+```
+
 ```@autodocs
 Modules = [OCReract]
 Private = false

src/OCReract.jl

@@ -1,7 +1,9 @@
 module OCReract
 
 export
-    run_tesseract
+    run_tesseract,
+    get_tesseract_version,
+    check_tesseract_installed
 
 include("tesseract.jl")
 

src/tesseract.jl

@@ -3,14 +3,27 @@ using ImageCore
 using Logging
 
 export
-    run_tesseract
+    run_tesseract,
+    get_tesseract_version,
+    check_tesseract_installed
 
 # Tesseract settings
 command = "tesseract"
 psm_valid_range = 0:14
 oem_valid_range = 0:4
 
-"""Util to check and inform whether Tesseract is installed or not"""
+"""
+  check_tesseract_installed()
+
+This function checks if Tesseract is installed in the system by running the command
+`$command --version`. If the command is not recognized, an error is logged.
+
+# Examples
+```julia-repl
+julia> using OCReract;
+julia> check_tesseract_installed()
+```
+"""
 function check_tesseract_installed()
     try
         read(`$command --version`, String);
@@ -21,7 +34,21 @@ end
 
 check_tesseract_installed()
 
-"""Util to get version of Tesseract installed"""
+"""
+    get_tesseract_version() -> String
+
+Function to get the version of Tesseract installed in the system.
+The version is extracted from the first line of the output of the command `$command --version`.
+
+# Returns
+- `String`: version of Tesseract installed
+
+# Examples
+```julia-repl
+julia> using OCReract;
+julia> get_tesseract_version()
+```
+"""
 function get_tesseract_version()
     info = read(`$command --version`, String)
     version = split(info, "\n")[1]

test/test_tesseract.jl

@@ -116,6 +116,13 @@ end
 function test_get_tesseract_version()
     version = OCReract.get_tesseract_version()
     tesseract_string, version_string = split(version, " ")
+    # Remove v from version string if it exists
+    if tesseract_string == "tesseract" && version_string[1] == 'v'
+        version_string = version_string[2:end]
+    end
+    # Use only the version number (major.minor.patch)
+    version_string = split(version_string, ".")[1:3]
+    version_string = join(version_string, ".")
     @test tesseract_string == "tesseract"
     @test occursin(r"^([1-9]\d*|0)(\.(([1-9]\d*)|0)){2}$", version_string)
 end