Skip to content

Commit

Permalink
Added Kanji readings for verbs
Browse files Browse the repository at this point in the history
  • Loading branch information
@hopto-dot
hopto-dot committed Jul 21, 2020
1 parent 3da9b6f commit fe23bd4
Showing 1 changed file with 163 additions and 14 deletions.
177 changes: 163 additions & 14 deletions Japanese Conjugation Helper/Module1.vb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1252,13 +1252,8 @@ Module Module1
End If




'Proper Example Sentence extraction:
'WordURL = ("https://jisho.org/search/" & ActualSearchWord & "%20%23sentences")

'Example Sentence extraction:
HTMLTemp = Client.DownloadString(New Uri(WordURL))

SentenceExample = RetrieveClassRange(HTMLTemp, "<li class=" & QUOTE & "clearfix" & QUOTE & "><span class=" & QUOTE & "furigana" & QUOTE & ">", "inline_copyright", "Example Sentence") 'Firstly extracting the whole group
If SentenceExample.Length > 10 Then
Example = ExampleSentence(SentenceExample) 'This group then needs all the "fillers" taken out, that's what the ExampleSentence function does
Expand All @@ -1267,17 +1262,19 @@ Module Module1
Console.WriteLine(Example)



Console.BackgroundColor = ConsoleColor.White
Console.ForegroundColor = ConsoleColor.Black
Console.WriteLine("Kanji:")
Console.BackgroundColor = ConsoleColor.Black
Console.ForegroundColor = ConsoleColor.White
'Kanji, meanings and reading extract. First open the "/word" page and then extracts instead of extracting from "/search":
Dim WordWordURL As String = ("https://jisho.org/word/" & ActualSearchWord)
Dim WordHTML As String
WordHTML = Client.DownloadString(New Uri(WordWordURL))




'Kanji, meanings and reading extract. First open the "/word" page and then extracts instead of extracting from "/search":
Dim KanjiInfo As String = RetrieveClassRange(WordHTML, "<span class=" & QUOTE & "character literal japanese_gothic", "</aside>", "KanjiInfo")


Dim KanjiGroupEnd As Integer 'This is going to detect "Details" (the end of a group of kanji info for one kanji)
Dim KanjiGroup(0) As String 'This will store each Kanji group in an array
Dim I As Integer = -1 'This will store the index of which kanji group the loop is on, indexing starts at 0, thus " = 0"
Expand Down Expand Up @@ -1315,6 +1312,8 @@ Module Module1
AllOn = False
Dim LastReadingFound As Boolean = False 'This is used to find the last reading of a kanji, it knows that it is a last because it ends in "</a>、" and not "</a>"
Dim JustEng As String
Dim KunReading, OnReading, ReadingSnip As String

KanjiGroup(KanjiGroup.Length - 1) = Mid(KanjiGroup(KanjiGroup.Length - 1), 5) 'This lets the last group work

For Looper = 0 To KanjiGroup.Length - 1
Expand Down Expand Up @@ -1348,8 +1347,6 @@ Module Module1
ActualInfo(Looper, 1) = JustEng

'Splitting the rest of the HTML (KanjiGroup) into Kun and On readings:
Dim KunReading, OnReading, ReadingSnip As String

FirstFinder = KanjiGroup(Looper).IndexOf("on readings") - 12
KunReading = Left(KanjiGroup(Looper), FirstFinder)
OnReading = Mid(KanjiGroup(Looper), FirstFinder)
Expand Down Expand Up @@ -1404,7 +1401,9 @@ Module Module1
End If
Loop

Console.BackgroundColor = ConsoleColor.DarkGray
Console.WriteLine(ActualInfo(Looper, 0) & " - " & ActualInfo(Looper, 1))
Console.BackgroundColor = ConsoleColor.Black
Console.WriteLine(ActualInfo(Looper, 2))
Console.WriteLine(ActualInfo(Looper, 3))
Console.WriteLine()
Expand Down Expand Up @@ -1785,6 +1784,156 @@ Module Module1
Console.WriteLine(Example)

Console.WriteLine()


Console.BackgroundColor = ConsoleColor.White
Console.ForegroundColor = ConsoleColor.Black
Console.WriteLine("Kanji:")
Console.BackgroundColor = ConsoleColor.Black
Console.ForegroundColor = ConsoleColor.White

'Kanji, meanings and reading extract. First open the "/word" page and then extracts instead of extracting from "/search":
Dim WordWordURL As String = ("https://jisho.org/word/" & PlainVerb)
Dim WordHTML As String
WordHTML = Client.DownloadString(New Uri(WordWordURL))

Dim KanjiInfo As String = RetrieveClassRange(WordHTML, "<span class=" & QUOTE & "character literal japanese_gothic", "</aside>", "KanjiInfo")

Dim KanjiGroupEnd As Integer 'This is going to detect "Details" (the end of a group of kanji info for one kanji)
Dim KanjiGroup(0) As String 'This will store each Kanji group in an array
Dim I As Integer = -1 'This will store the index of which kanji group the loop is on, indexing starts at 0, thus " = 0"
Dim LastDetailsIndex As Integer = KanjiInfo.LastIndexOf("Details")
KanjiInfo = Left(KanjiInfo, LastDetailsIndex)

Dim Finished As Boolean = False
Do Until Finished = True 'Do until no more end splitters can be found. The sentences that are pasted won't end in "|" because of how the AHK sentence grabber works
I += 1
Array.Resize(KanjiGroup, KanjiGroup.Length + 1)
KanjiGroupEnd = KanjiInfo.IndexOf("Details") + 10
If KanjiGroupEnd = 9 Then '(-1 but at add because of the above line. This means if "Details" isn't found
KanjiGroup(I) = KanjiInfo
Finished = True
Continue Do
End If

KanjiGroup(I) = Mid(KanjiInfo, 6, KanjiGroupEnd - 5)
KanjiInfo = Mid(KanjiInfo, KanjiGroupEnd)
Loop
Array.Resize(KanjiGroup, KanjiGroup.Length - 1)

Dim ActualInfo(KanjiGroup.Length - 1, 3) 'X = Kanji (group), Y = Info type.
'Y indexs:
'0 = Kanji
'1 = English meaning(s) (I will concatinate multiple meanings)
'2 = kun readings (concatentated if needed, usually so)
'3 = on readings (concatentated if needed, usually so)
Dim FirstFinder As Integer
Dim SecondFinder As Integer

Dim AllEng, AllKun, AllOn As Boolean
AllEng = False
AllKun = False
AllOn = False
Dim LastReadingFound As Boolean = False 'This is used to find the last reading of a kanji, it knows that it is a last because it ends in "</a>、" and not "</a>"
Dim JustEng As String
Dim KunReading, OnReading, ReadingSnip As String

KanjiGroup(KanjiGroup.Length - 1) = Mid(KanjiGroup(KanjiGroup.Length - 1), 5) 'This lets the last group work

For Looper = 0 To KanjiGroup.Length - 1
FirstFinder = KanjiGroup(Looper).IndexOf("</a>")
'KanjiGroup(Looper) = Mid(KanjiGroup(Looper), FirstFinder + 10)
ActualInfo(Looper, 0) = Mid(KanjiGroup(Looper), FirstFinder, 1)

FirstFinder = KanjiGroup(Looper).IndexOf("sense")
KanjiGroup(Looper) = Mid(KanjiGroup(Looper), FirstFinder + 10)

FirstFinder = KanjiGroup(Looper).IndexOf("</div>")


JustEng = Left(KanjiGroup(Looper), FirstFinder)

JustEng = Mid(JustEng, 18)
JustEng = Left(JustEng, JustEng.Length - 14)
KanjiGroup(Looper) = KanjiGroup(Looper).Replace(JustEng, "")

JustEng = JustEng.Replace(" ", "")
FirstFinder = JustEng.IndexOf("</span>")
SecondFinder = JustEng.IndexOf("<span>")
Try
JustEng = JustEng.Replace(Mid(JustEng, FirstFinder, SecondFinder + 7 - FirstFinder), "")
Catch
End Try

JustEng = JustEng.Replace(",", ", ")
JustEng = Left(JustEng, 1).ToUpper & Mid(JustEng, 2)

ActualInfo(Looper, 1) = JustEng

'Splitting the rest of the HTML (KanjiGroup) into Kun and On readings:


FirstFinder = KanjiGroup(Looper).IndexOf("on readings") - 12
KunReading = Left(KanjiGroup(Looper), FirstFinder)
OnReading = Mid(KanjiGroup(Looper), FirstFinder)

ActualInfo(Looper, 2) &= "Kun Readings: "
ActualInfo(Looper, 3) &= "On Readings: "

LastReadingFound = False
Do Until LastReadingFound = True
If KunReading.IndexOf("</a>、") <> -1 Then 'If the reading that is about to be snipped isn't the last
SecondFinder = KunReading.IndexOf("</a>、")
FirstFinder = Left(KunReading, SecondFinder).LastIndexOf(">")
ReadingSnip = Mid(KunReading, FirstFinder + 2, SecondFinder - 1 - FirstFinder)

ActualInfo(Looper, 2) &= ReadingSnip & ", " 'Adding the reading to the Actual info array

KunReading = Mid(KunReading, SecondFinder + 10)

ElseIf KunReading.IndexOf("</a><") <> -1 Then 'If it is the last, "<" is just the beginning of "</span>"
SecondFinder = KunReading.IndexOf("</a>")
FirstFinder = Left(KunReading, SecondFinder).LastIndexOf(">")
ReadingSnip = Mid(KunReading, FirstFinder + 2, SecondFinder - 1 - FirstFinder)

ActualInfo(Looper, 2) &= ReadingSnip 'Adding the reading to the Actual info array

LastReadingFound = True
Else
LastReadingFound = True
End If
Loop
LastReadingFound = False
Do Until LastReadingFound = True
If OnReading.IndexOf("</a>、") <> -1 Then 'If the reading that is about to be snipped isn't the last
SecondFinder = OnReading.IndexOf("</a>、")
FirstFinder = Left(OnReading, SecondFinder).LastIndexOf(">")
ReadingSnip = Mid(OnReading, FirstFinder + 2, SecondFinder - 1 - FirstFinder)

ActualInfo(Looper, 3) &= ReadingSnip & ", " 'Adding the reading to the Actual info array

OnReading = Mid(OnReading, SecondFinder + 10)

ElseIf OnReading.IndexOf("</a><") <> -1 Then 'If it is the last, "<" is just the beginning of "</span>"
SecondFinder = OnReading.IndexOf("</a>")
FirstFinder = Left(OnReading, SecondFinder).LastIndexOf(">")
ReadingSnip = Mid(OnReading, FirstFinder + 2, SecondFinder - 1 - FirstFinder)

ActualInfo(Looper, 3) &= ReadingSnip 'Adding the reading to the Actual info array

LastReadingFound = True
Else
LastReadingFound = True
End If
Loop
Console.BackgroundColor = ConsoleColor.DarkGray
Console.WriteLine(ActualInfo(Looper, 0) & " - " & ActualInfo(Looper, 1))
Console.BackgroundColor = ConsoleColor.Black
Console.WriteLine(ActualInfo(Looper, 2))
Console.WriteLine(ActualInfo(Looper, 3))
Console.WriteLine()
Next

Console.ReadLine()
Main()
End Sub
Expand Down Expand Up @@ -2108,7 +2257,7 @@ Module Module1

End Function
Function WordLinkScraper(ByVal URL) 'This is for getting the definition of a word from the page of the word instead of the search results, this is much more reliable for definitions
Const QUOTE = """"
'Const QUOTE = """"

Dim Client As New WebClient
Client.Encoding = System.Text.Encoding.UTF8
Expand Down

0 comments on commit fe23bd4

Please sign in to comment.