From 9643c51f416d32851fce6b36a9a269b02d57f21e Mon Sep 17 00:00:00 2001
From: psachin
Date: Wed, 31 Jul 2013 12:20:13 +0530
Subject: Subject: sorting of file-names w.r.t chapter number

Description:

- sorting
- added usage in ReadMe.md
---
 ReadMe.md | 55 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 auto.sh   | 20 +++++++++++++++++++-
 2 files changed, 73 insertions(+), 2 deletions(-)

diff --git a/ReadMe.md b/ReadMe.md
index 549eb83..ecff640 100644
--- a/ReadMe.md
+++ b/ReadMe.md
@@ -1,4 +1,57 @@
 # tbc-auto-checker
 ### Auto checker script for Scilab Textbook Companion.
 
-### Please visit [http://scilab.in/Textbook_Companion_Project](http://scilab.in/Textbook_Companion_Project) for more info.
+### Usage
+
+* Clone this repository 
+
+```bash
+git clone https://github.com/Scilab-India/tbc-auto-checker.git
+```
+
+* Change path to this directory
+
+```bash
+cd tbc-auto-checker
+```
+
+* Place ZIP file(s) of book(s) in this directory and run the script
+
+```bash
+bash auto.sh
+```
+
+### Output
+
+* The output log files and error log files will be generated
+separately.
+
+#### text output
+
+* Text output will be stored in `output_<book-name>.log` file.
+
+#### graph output
+
+* You have to set a variable `SCI_GRAPH_PATH` to a path where you want
+all the graphs to be stored.
+
+* Graphs with text output will be stored in
+  `output_graph_<book-name>.log` file
+  
+#### errors
+
+* **for text based errors**: `error_<book-name>.log`
+
+* **for graph based errors**: `error_graph_<book-name>.log`
+
+#### Warning
+
+* All output are first stored in a variable and then written to
+  respective files. You may run out of memory sometimes.
+
+#### Site
+
+Please visit
+[http://scilab.in/Textbook_Companion_Project](http://scilab.in/Textbook_Companion_Project)
+for more info.
+
diff --git a/auto.sh b/auto.sh
index be67efc..6e01b6a 100755
--- a/auto.sh
+++ b/auto.sh
@@ -52,7 +52,25 @@ function scan_sce_for_errors() {
 
     # make a list of all .sce file(with complete path). Exclude
     # scanning 'DEPENDENCIES' DIR
-    SCE_FILE_LIST=$(find ${ZIPFILE} -type f -iname "*.sce" ! -path "*/DEPENDENCIES*")
+
+    # That awk command says the field separator FS is set to /; this
+    # affects the way it reads fields. The output field separator OFS
+    # is set to "."; this affects the way it prints records. This is
+    # intentionally done so that 'cut' will take "." as a field
+    # Seperator during final sort operation. The next statement says
+    # print the last column (NF is the number of fields in the record,
+    # so it also happens to be the index of the last field) as well as
+    # the whole record ($0 is the whole record); it will print them
+    # with the OFS between them. Then the list is sorted, treating _
+    # as the field separator - since we have the filename first in the
+    # record, it will sort by that. Then the cut prints only fields 3
+    # through the end, again treating "." as the field separator.
+
+    SCE_FILE_LIST=$(find ${ZIPFILE} -type f -iname "*.sce" ! \
+	-path "*/DEPENDENCIES*" | \
+	awk -vFS=/ -vOFS="." '{print $NF,$0}' | \
+	sort -n -t _ -k1 -k2 | cut -d"." -f3-)
+    
     SCE_FILE_COUNT=$(echo "${SCE_FILE_LIST}" | wc -l)
     echo -e "Total number of .sce files(without counting DEPENDENCIES directory): ${SCE_FILE_COUNT}\n" >> ./output_${ZIPFILE}.log 
 
-- 
cgit