From e2da0fb83970a105d5e0d6849e16558162313728 Mon Sep 17 00:00:00 2001
From: Patrick Jentsch <p.jentsch@uni-bielefeld.de>
Date: Fri, 26 Mar 2021 10:03:59 +0100
Subject: [PATCH] Tweak the README and pipeline help.

---
 README.md | 50 +-------------------------------------------------
 ocr       |  2 +-
 2 files changed, 2 insertions(+), 50 deletions(-)

diff --git a/README.md b/README.md
index e59b8b8..265cbd8 100644
--- a/README.md
+++ b/README.md
@@ -20,7 +20,7 @@ mkdir -p /<my_data_location>/input /<my_data_location>/output
 
 2. Place your PDF files inside `/<my_data_location>/input`. Files should all contain text of the same language.
 
-3. Start the pipeline process. Check the [Pipeline arguments](#pipeline-arguments) section for more details.
+3. Start the pipeline process. Check the pipeline help (`ocr --help`) for more details.
 ```
 # Option one: Use the wrapper script
 ## Install the wrapper script (only on first run). Get it from https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr/-/raw/development/wrapper/ocr, make it executeable and add it to your ${PATH}
@@ -42,51 +42,3 @@ docker run \
 ```
 
 4. Check your results in the `/<my_data_location>/output` directory.
-
-### Pipeline arguments
-
-#### Mandatory arguments
-
-`-i, --input-dir INPUT_DIR`
-* Input directory
-
-`-o, --output-dir OUTPUT_DIR`
-* Output directory
-
-`-l, --language {spa,fra,dan,deu,eng,frm,chi_tra,ara,enm,ita,ell,frk,rus,por}`
-* Language of the input (3-character ISO 639-2 language codes)
-
-#### Optional arguments
-
-`--binarize`
-* Add binarization as a preprocessing step
-
-`--log-dir`
-* Logging directory
-
-`--mem-mb`
-* Amount of system memory to be used (Default: min(--n-cores * 2048, available system memory))
-
-`--n-cores`
-* Number of CPU threads to be used (Default: min(4, available CPU cores))
-
-`-v, --version`
-* Returns the current version of the OCR pipeline
-
-``` bash
-# Example with all arguments used
-docker run \
-    --rm \
-    -it \
-    -u $(id -u $USER):$(id -g $USER) \
-    -v /<my_data_location>/input:/ocr_pipeline/input \
-    -v /<my_data_location>/output:/ocr_pipeline/output \
-    -v /<my_data_location>/logs:/ocr_pipeline/logs \
-    gitlab.ub.uni-bielefeld.de:4567/sfb1288inf/ocr:development \
-        -i /ocr_pipeline/input \
-        -l eng \
-        -o /ocr_pipeline/output \
-        --binarize \
-        --log-dir /ocr_pipeline/logs \
-        --n-cores 8 \
-```
diff --git a/ocr b/ocr
index 262a758..e15967a 100755
--- a/ocr
+++ b/ocr
@@ -322,7 +322,7 @@ def parse_args():
                         type=int)
     parser.add_argument('--n-cores',
                         default=min(4, multiprocessing.cpu_count()),
-                        help='Number of CPU threads to be used',
+                        help='Number of CPU threads to be used (Default: min(4, number of CPUs))',  # noqa
                         type=int)
     parser.add_argument('--zip',
                         help='Create one zip file per filetype')