xmlDB

package module
v0.0.0-...-e7e6104 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: May 7, 2024 License: BSD-2-Clause Imports: 6 Imported by: 7

README

About

This is a Go package to treat xml as a native database. You can access, modify or replace node

Usage

  1. Declare Database.

    var DB *xmlDB.Database = new(xmlDB.Database)

  2. Load Database.

    xmlDB.Load_db(DB, "sample.html")

Content of sample.html

<!DOCTYPE html>
<html>
   <head>
      <title>This is document title</title>
   </head>	
   <body style="123">
      <h1>This is a heading</h1>
      <p>Hello World!</p>
   </body>	
</html>

  1. Identifying Nodes using Query.

    identifiedNodes, _ := xmlDB.GetNode(DB, 0, "head*/title[This is document title]")

    • 'identifiedNodes' contains list of nodes ids(<head>) identified under parent node with id '0' (<html> ..</html>).
    • '*' marks the node we require.
    • [] encloses attribute or value of the node as additional search criteria.

  2. Getting Content of identified nodes.

    for _,node:=range identifiedNodes {
        fmt.Printf("\n%s",xmlDB.GetNodeContents(DB, node))
    }

Output

    <head>
          <title>This is document title</title>
    </head>
  1. Getting Value of identified nodes.
   identifiedNodes, _ := xmlDB.GetNode(DB, 0, "head/title*")
   for _,node:=range identifiedNodes {
        fmt.Printf("\n%s",xmlDB.GetNodeValue(DB, node))
   }

Output

This is document title

  1. Searching using attribute value.

    identifiedNodes, _ = xmlDB.GetNode(DB, 0, "<x>*[style=\"123\"]/h1")

  2. Updating node

	fmt.Printf("\n### Updating node ##\n")
	identifiedNodes, _ = xmlDB.GetNode(DB, 0, "head/title")
	for _, node := range identifiedNodes {
		newnodes := xmlDB.ReplaceNode(DB, node, "<title>test</title>")
		fmt.Printf("After updation\n")
		fmt.Printf("old node value- %s", xmlDB.GetNodeValue(DB, node)) //no output, existing id is removed and new id added
		fmt.Printf("\nnew node value- %s", xmlDB.GetNodeValue(DB, newnodes[0]))
	}
	fmt.Printf("\n### Updating node attribute##\n")
	identifiedNodes, _ = xmlDB.GetNode(DB, 0, "<x>*[style=\"123\"]/h1")
	for _, node := range identifiedNodes {
		fmt.Printf("\n%s", xmlDB.GetNodeAttribute(DB, node, "style"))
		xmlDB.UpdateAttributevalue(DB, node, "style", "test2")
		fmt.Printf("\nafter updating Attribute-\n%s", xmlDB.GetNodeContents(DB, node))
		xmlDB.UpdateAttributevalue(DB, node, "label", "value")
		fmt.Printf("\nafter adding Attribute-\n%s", xmlDB.GetNodeContents(DB, node))

	}

Output

### Updating node ##
After updation
Warning :node  doesnot exist
old node value- 
new node value- test
### Updating node attribute##

123
after updating Attribute-
<body style="test2">
  <h1>This is a heading with style</h1>
  <p>Hello World!</p>
</body>

after adding Attribute-
<body style="test2" label="value">
  <h1>This is a heading with style</h1>
  <p>Hello World!</p>
</body>

  1. Recursive search.

    identifiedNodes, _ = xmlDB.GetNode(DB, 0, "../h1")

Also see Example :"https://github.com/LIJUCHACKO/ods2csv". I have used this library to parse ods xml content.

Working/Software Design

INPUT(sample)
<!DOCTYPE html>
<html>
   <head><title>This is document title</title></head>	
   <body style="123">
      <h1>This is a heading</h1>
      <p>Hello World!</p>
   </body>	
</html>
After parsing- global variables are filled as shown
global_dbLines global_ids global_paths global_values global_attributes
<!DOCTYPE html> -1
<head> 0 /head
<title>This is document title</title> 1 /head/title This is document title
<\head> 2 /head/~
<body style="123" font="arial"> 3 /body style="123"|| font="arial"
<h1>This is a heading</h1> 4 /body/h1
<p>Hello World!</p> 5 /body/p This is a heading
</body> 6 /body/~ Hello World!

Note:- If a new node is inserted in between, global_id '7' will be assigned to it. global_id will be unique and will be retained till the node is deleted.

'nodeNoToLineno' contains line no for every global id.
index/global_id nodeNoToLineno[index]
0 1
1 2
2 3
3 4
'Nodeendlookup' contains global_id of the node end.
index/global_id Nodeendlookup[index]
0 2
1 1
2 2
3 6
4 4
5 5
'pathKeylookup' is for quick lookup for line nos corresponding to innermost node.

-Say the path is '/head/title' then hash is calculated for 'title'.

-Corresponding to the hash value a list of global_ids ,arranged in the increasing order of lineno, is stored.

Hash no global id list corresponding to the hash
0
1
2 [id1,id2,id3,id4]

-Binary search is utilised to find ids, under a parent node, from this list.

Documentation

Index

Constants

View Source 
const SEGMENTSIZE = 2000

Variables

This section is empty.

Functions

func AppendAfterNode 

func AppendAfterNode(DB *Database, nodeId int, sub_xml string) ([]int, error)

func AppendBeforeNode 

func AppendBeforeNode(DB *Database, nodeId int, sub_xml string) ([]int, error)

func ChildNodes 

func ChildNodes(DB *Database, nodeId int) []int

func CutPasteAsSubNode 

func CutPasteAsSubNode(DB *Database, UnderId int, nodeId int) error

func Dump_DB 

func Dump_DB(DB *Database) string

func GetAllNodeAttributes 

func GetAllNodeAttributes(DB *Database, nodeId int) ([]string, []string)

func GetListofWithAttribute 

func GetListofWithAttribute(DB *Database, Attribute string) []int

func GetNode 

func GetNode(DB *Database, parent_nodeId int, QUERY_inp string) ([]int, []string)

func GetNodeAttribute 

func GetNodeAttribute(DB *Database, nodeId int, label string) string

func GetNodeContentRaw 

func GetNodeContentRaw(DB *Database, nodeId int) string

func GetNodeContents 

func GetNodeContents(DB *Database, nodeId int) string

func GetNodeName 

func GetNodeName(DB *Database, nodeId int) string

func GetNodeValue 

func GetNodeValue(DB *Database, nodeId int) string

func Get_common 

func Get_common(set1 []int, set2 []int) []int

func InserSubNode 

func InserSubNode(DB *Database, nodeId int, sub_xml string) ([]int, error)

func IslowestNode 

func IslowestNode(DB *Database, nodeId int) bool

func Load_db 

func Load_db(DB *Database, filename string) error

func Load_dbcontent 

func Load_dbcontent(DB *Database, xmllines []string)

func LocateRequireParentdNode 

func LocateRequireParentdNode(DB *Database, parent_nodeLine int, RequiredPath string, LineNo_inp int) int

func MergeNodes 

func MergeNodes(DB *Database, fromNodeId int, toNodeId int) error

func NextNode 

func NextNode(DB *Database, nodeId int) int

func NodeDebug 

func NodeDebug(DB *Database, nodeId int)

func NodeEnd 

func NodeEnd(DB *Database, nodeId int) int

func NodeLine 

func NodeLine(DB *Database, nodeId int) int

func ParentNode 

func ParentNode(DB *Database, nodeId int) int

func RemoveNode 

func RemoveNode(DB *Database, nodeId int) []int

func ReplaceHTMLSpecialEntities 

func ReplaceHTMLSpecialEntities(input string) string

func ReplaceNode 

func ReplaceNode(DB *Database, nodeId int, sub_xml string) ([]int, error)

func ReplacewithHTMLSpecialEntities 

func ReplacewithHTMLSpecialEntities(DB *Database, input string) string

func SaveAs_DB 

func SaveAs_DB(DB *Database, filename string)

func Save_DB 

func Save_DB(DB *Database)

func UpdateAttributevalue 

func UpdateAttributevalue(DB *Database, nodeId int, label string, value string) ([]int, error)

func UpdateNodevalue 

func UpdateNodevalue(DB *Database, nodeId int, new_value string) ([]int, error)

Types

type Database 

type Database struct {
	Debug_enabled  bool
	Libreofficemod bool

	Nodeendlookup []int

	MaxNooflines int

	WriteLock bool
	// contains filtered or unexported fields
}

Source Files

View all Source files

Directories

Path Synopsis

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.