add test samples to opale_to_basex

hdoc_to_basex/README.md

@@ -33,20 +33,20 @@ User stories
 Step by step :
 
 	[`Step 1 : File transformation`]
-		1. Put the files .hdoc you want to deal with in the folder [input](https://gitlab.utc.fr/crozatst/hdoc/tree/master/hdoc_to_basex/input)
-		2. Run the transformation progam (Win : double click run.bat, Linux : execute run.sh)
-		3. This transformation includes :
+		- Put the files .hdoc you want to deal with in the folder [`input`](https://gitlab.utc.fr/crozatst/hdoc/tree/master/hdoc_to_basex/input)
+		- Run the transformation progam (Win : double click run.bat, Linux : execute run.sh)
+		- This transformation includes :
 			* Title, authors, keywords
 			* First Level section : title, type, paragraphs
 	
 	[`Step 2 : Create data base in basex`]
-		1. Download and install [BaseX](http://basex.org/products/download/all-downloads/)
-		2. Run BasexGui
-		3. In the Text Editor of BaseX, open the command script "createbd.bxs" in folder [`command`](https://gitlab.utc.fr/crozatst/hdoc/tree/master/hdoc_to_basex/basex/command).
+		- Download and install [BaseX](http://basex.org/products/download/all-downloads/)
+		- Run BasexGui
+		- In the Text Editor of BaseX, open the command script "createbd.bxs" in folder [`command`](https://gitlab.utc.fr/crozatst/hdoc/tree/master/hdoc_to_basex/basex/command).
 		  Follow the instructions in the script, and then execute it.
 	
 	[`Step 3 : Make XQuery request`]
-		1. In the Text Editor of BaseX, you can open and execute xquery script "main.xq" in folder [`xquery`](https://gitlab.utc.fr/crozatst/hdoc/tree/master/hdoc_to_basex/basex/xquery).
+		- In the Text Editor of BaseX, you can open and execute xquery script "main.xq" in folder [`xquery`](https://gitlab.utc.fr/crozatst/hdoc/tree/master/hdoc_to_basex/basex/xquery).
 		  It's in this main module that we call predefined functions and execute script
 		  
 		- .xqm files are library modules where we have defined functions, we can go to these files for more detailed using instructions
@@ -58,13 +58,13 @@ Step by step :
 
 TODO List
 ------------------
-	1. xlst Transformation :
+	- xlst Transformation :
 		* Remove text formats
 		* Sub sections
 		* Exercices
 		* Resources : images, ...
 	
-	2. XQuery requests :
+	- XQuery requests :
 		* Search keywords in text 
 		* Search sub sections by keywords in their titles
 		* Search exercices by keywords in their titles
\ No newline at end of file

opale_to_basex/.gitignore

+!input/.gitkeep
+!output/.gitkeep
\ No newline at end of file

opale_to_basex/README.md

@@ -34,14 +34,14 @@ Please consult the section "User Stories" of README.md file in [`hdoc_to_basex`]
 Step by step :
 
 	[`Step 1 : File transformation`]
-		- Put the files .scar you want to deal with in the folder [input](https://gitlab.utc.fr/crozatst/hdoc/tree/master/opale_to_basex/input)
+		- Put the files .scar you want to deal with in the folder [`input`](https://gitlab.utc.fr/crozatst/hdoc/tree/master/opale_to_basex/input)
 		- Run the transformation progam (Win : double click run.bat, Linux : execute run.sh)
 		- This transformation includes :
 			* Title, authors, keywords
 			* First Level section : title, type
 	
 	[`Step 2 : Create data base in basex`]
-		- Download and install [BaseX](http://basex.org/products/download/all-downloads/)
+		- Download and install [`BaseX`](http://basex.org/products/download/all-downloads/)
 		- Run BasexGui
 		- In the Text Editor of BaseX, open the command script "createbd.bxs" in folder [`command`](https://gitlab.utc.fr/crozatst/hdoc/tree/master/opale_to_basex/basex/command).
 		  Follow the instructions in the script, and then execute it.

opale_to_basex/basex/command/createdb.bxs

+# This script will a database that includes all the xml files in the folder /hdoc_to_basex/output automatically
+# Before executing this script, please make sure that you have successfully finished the transformation in the step 1 in the part "user story" of the README.md
+# Syntax : CREATE DB [name] ([input])
+
+#CREATE DB myDB [..the repertory of the projet in your local disk..]/hdoc/hdoc_to_basex/output
+
+# Example : 
+CREATE DB myDB D:/School/UTC/GI04/NF29/Projet/hdoc/hdoc_to_basex/output
+
+# P.S. If you get error message : Resource "..." not found, please confirm your file repertory is correct
\ No newline at end of file

opale_to_basex/basex/xquery/main.xq

+(: this script with .xq as suffix is the main module :)
+(: all functions defined in .xqm files (library modules) can be called here :)
+
+import module namespace myNs = "https://gitlab.utc.fr/crozatst/hdoc/tree/master/hdoc_to_basex" at "searchSectionByTitle.xqm", "searchSectionByTitle.xqm", "searchDocByAuthor.xqm";
+
+(: myNs:searchDocByTitle('^NF29_HdocEtherpad$', //document ):)
+(: myNs:searchSectionByTitle('contenu', //document) :)
+(: myNs:searchDocByAuthor('montangé', //document) :)
+
+myNs:searchSectionByTitle('xml', myNs:searchDocByAuthor('montangé', //document))
\ No newline at end of file

opale_to_basex/basex/xquery/searchDocByAuthor.xqm

+(: This script will return documents by searching its author :)
+(: We can assign a Regular Expression to the variable $author :)
+(: For example, $name := '^Baptiste Montangé$', to search for an exact name:)
+(: For example, $name := 'Montangé', to search for documents whose author named Coutant:)
+(: Remark : case and accents in author's name have been taken care of :)
+
+module namespace myNs = "https://gitlab.utc.fr/crozatst/hdoc/tree/master/hdoc_to_basex";
+
+declare function myNs:searchDocByAuthor($name as xs:string, $docs as node()*) as node()*
+{
+  let $name_noAcc := translate($name, 'áàâäéèêëíìîïóòôöúùûüABCDEFGHIJKLMNOPQRSTUVWXYZ','aaaaeeeeiiiioooouuuuabcdefghijklmnopqrstuvwxyz')
+  for $doc in $docs
+  return
+    for $author in $doc/authors/author
+    let $titre := $doc/titre
+    let $author_noAcc := translate($author, 'áàâäéèêëíìîïóòôöúùûüABCDEFGHIJKLMNOPQRSTUVWXYZ','aaaaeeeeiiiioooouuuuabcdefghijklmnopqrstuvwxyz')
+    where matches($author_noAcc, $name_noAcc)
+    group by $titre (: Avoid duplications of documents by their titre:)
+    return $doc
+};
\ No newline at end of file

opale_to_basex/basex/xquery/searchDocByTitle.xqm

+(: This script will return documents by searching one keyword in their title :)
+(: We can assign a Regular Expression to the variable $name :)
+(: For example, $name := '^NF29_HdocEtherpad$', to search for an exact name:)
+(: For example, $name := 'NF29', to search for documents whose name contains 'NF29':)
+
+module namespace myNs = "https://gitlab.utc.fr/crozatst/hdoc/tree/master/hdoc_to_basex";
+
+declare function myNs:searchDocByTitle($name as xs:string, $docs as node()*) as node()*
+{
+  for $doc in $docs
+  where matches($doc/titre, $name, "i")
+  return $doc
+};
\ No newline at end of file

opale_to_basex/basex/xquery/searchSectionByTitle.xqm

+(: This script will return a section by searching keyword in its title :)
+(: We can assign a Regular Expression to the variable $keyword :)
+(: For example, $keyword := '^Objectifs$', to search for sections whose titles are exactly "Objectifs":)
+(: For example, $keyword := 'Syntax', to search for sections whose titles containing "Syntax" :)
+(: Remark : case and accents in the keyword have been taken care of  :)
+
+module namespace myNs = "https://gitlab.utc.fr/crozatst/hdoc/tree/master/hdoc_to_basex";
+
+declare function myNs:searchSectionByTitle($keyword as xs:string, $docs as node()*) as node()*
+{
+  let $keyword_noAcc := translate($keyword, 'áàâäéèêëíìîïóòôöúùûüABCDEFGHIJKLMNOPQRSTUVWXYZ','aaaaeeeeiiiioooouuuuabcdefghijklmnopqrstuvwxyz')
+  for $doc in $docs
+  return
+    for $section in $doc/sections/section
+    let $title_noAcc := translate($section/titresection, 'áàâäéèêëíìîïóòôöúùûüABCDEFGHIJKLMNOPQRSTUVWXYZ','aaaaeeeeiiiioooouuuuabcdefghijklmnopqrstuvwxyz')
+    where matches($title_noAcc, $keyword_noAcc)
+    return $section
+};
\ No newline at end of file