问题
I'm processing data from government sources (FEC, state voter databases, etc). It's inconsistently malformed, which breaks my CSV parser in all sorts of delightful ways.
It's externally sourced and authoritative. I must parse it, and I cannot have it re-input, validated on input, or the like. It is what it is; I don't control the input.
Properties:
- Fields contain malformed UTF-8 (e.g.
Foo \xAB bar) - The first field of a line specifies the record type from a known set. Knowing the record type, you know how many fields there are and their respective data types, but not until you do.
- Any given line within a file might use quoted strings (
"foo",123,"bar") or unquoted (foo,123,bar). I haven't yet encountered any where it's mixed within a given line (i.e."foo",123,bar) but it's probably in there. - Strings may include internal newline, quote, and/or comma character(s).
- Strings may include comma separated numbers.
- Data files can be very large (millions of rows), so this needs to still be reasonably fast.
I'm using Ruby FasterCSV (known as just CSV in 1.9), but the question should be language-agnostic.
My guess is that a solution will require preprocessing substitution with unambiguous record separator / quote characters (eg ASCII RS, STX). I've started a bit here but it doesn't work for everything I get.
How can I process this kind of dirty data robustly?
ETA: Here's a simplified example of what may be in single file:
"this","is",123,"a","normal","line" "line","with "an" internal","quote" "short line","with an "internal quote", 1 comma and linebreaks" un "quot" ed,text,with,1,2,3,numbers "quoted","number","series","1,2,3" "invalid \xAB utf-8"
回答1:
It is possible to subclass Ruby's File to process each line of the the CSV file before it is passed to the Ruby's CSV parser. For example, here's how I used this trick to replace non-standard backslash-escaped quotes \" with standard double-quotes ""
class MyFile < File
def gets(*args)
line = super
if line != nil
line.gsub!('\\"','""') # fix the \" that would otherwise cause a parse error
end
line
end
end
infile = MyFile.open(filename)
incsv = CSV.new(infile)
while row = incsv.shift
# process each row here
end
You could in principle do all sorts of additional processing, e.g. UTF-8 cleanups. The nice thing about this approach is you handle the file on a line by line basis, so you don't need to load it all into memory or create an intermediate file.
回答2:
First, here is a rather naive attempt: http://rubular.com/r/gvh3BJaNTc
/"(.*?)"(?=[\r\n,]|$)|([^,"\s].*?)(?=[\r\n,]|$)/m
The assumptions here are:
- A field may start with quotes. In which case, it should end with a quote that is either:
- before a comma
- before a new line (if it is last field on its line)
- before the end of the file (if it is last field on the last line)
- Or, its first character is not a quote, so it contains characters until the same condition as before is met.
This almost does what you want, but fails on these fields:
1 comma and linebreaks"
As TC had pointed out in the comments, your text is ambiguous. I'm sure you already know it, but for completeness:
"a"- is thataor"a"? How do you represent a value that you want to be wrapped in quotes?"1","2"- might be parsed as1,2, or as1","2- both are legal.,1 \n 2,- End of line, or newline in the value? You cannot tell, specially if this is supposed to be the last value of its line.1 \n 2 \n 3- One value with newlines? Two values (1\n2,3or1,2\n3)? Three values?
You may be able to get some clues if you examine the first value on each row, which as you have said, should tell you the number of columns and their types - this can give you the additional information you are missing to parse the file (for example, if you know there should another field in this line, then all newlines belong in the current value). Even then though, it looks like there are serious problems here...
回答3:
I made an app to reformat CSV files, doubling the single quotes inside fields and replacing the new lines inside them with a string like '\n'.
Once the data is inside the database we can replace back the '\n' to new lines.
I needed to do this because the apps I had to process CSV does not deal correctly with new lines.
Feel free to use and change.
In python:
import sys
def ProcessCSV(filename):
file1 = open(filename, 'r')
filename2 = filename + '.out'
file2 = open(filename2, 'w')
print 'Reformatting {0} to {1}...', filename, filename2
line1 = file1.readline()
while (len(line1) > 0):
line1 = line1.rstrip('\r\n')
line2 = ''
count = 0
lastField = ( len(line1) == 0 )
while not lastField:
lastField = (line1.find('","') == -1)
res = line1.partition('","')
field = res[0]
line1 = res[2]
count = count + 1
hasStart = False
hasEnd = False
if ( count == 1 ) and ( field[:1] == '"' ) :
field = field[1:]
hasStart = True
elif count > 1:
hasStart = True
while (True):
if ( lastField == True ) and ( field[-1:] == '"' ) :
field = field[:-1]
hasEnd = True
elif not lastField:
hasEnd = True
if lastField and not hasEnd:
line1 = file1.readline()
if (len(line1) == 0): break
line1 = line1.rstrip('\r\n')
lastField = (line1.find('","') == -1)
res = line1.partition('","')
field = field + '\\n' + res[0]
line1 = res[2]
else:
break
field = field.replace('"', '""')
line2 = line2 + iif(count > 1, ',', '') + iif(hasStart, '"', '') + field + iif(hasEnd, '"', '')
if len(line2) > 0:
file2.write(line2)
file2.write('\n')
line1 = file1.readline()
file1.close()
file2.close()
print 'Done'
def iif(st, v1, v2):
if st:
return v1
else:
return v2
filename = sys.argv[1]
if len(filename) == 0:
print 'You must specify the input file'
else:
ProcessCSV(filename)
In VB.net:
Module Module1
Sub Main()
Dim FileName As String
FileName = Command()
If FileName.Length = 0 Then
Console.WriteLine("You must specify the input file")
Else
ProcessCSV(FileName)
End If
End Sub
Sub ProcessCSV(ByVal FileName As String)
Dim File1 As Integer, File2 As Integer
Dim Line1 As String, Line2 As String
Dim Field As String, Count As Long
Dim HasStart As Boolean, HasEnd As Boolean
Dim FileName2 As String, LastField As Boolean
On Error GoTo locError
File1 = FreeFile()
FileOpen(File1, FileName, OpenMode.Input, OpenAccess.Read)
FileName2 = FileName & ".out"
File2 = FreeFile()
FileOpen(File2, FileName2, OpenMode.Output)
Console.WriteLine("Reformatting {0} to {1}...", FileName, FileName2)
Do Until EOF(File1)
Line1 = LineInput(File1)
'
Line2 = ""
Count = 0
LastField = (Len(Line1) = 0)
Do Until LastField
LastField = (InStr(Line1, """,""") = 0)
Field = Strip(Line1, """,""")
Count = Count + 1
HasStart = False
HasEnd = False
'
If (Count = 1) And (Left$(Field, 1) = """") Then
Field = Mid$(Field, 2)
HasStart = True
ElseIf Count > 1 Then
HasStart = True
End If
'
locFinal:
If (LastField) And (Right$(Field, 1) = """") Then
Field = Left$(Field, Len(Field) - 1)
HasEnd = True
ElseIf Not LastField Then
HasEnd = True
End If
'
If LastField And Not HasEnd And Not EOF(File1) Then
Line1 = LineInput(File1)
LastField = (InStr(Line1, """,""") = 0)
Field = Field & "\n" & Strip(Line1, """,""")
GoTo locFinal
End If
'
Field = Replace(Field, """", """""")
'
Line2 = Line2 & IIf(Count > 1, ",", "") & IIf(HasStart, """", "") & Field & IIf(HasEnd, """", "")
Loop
'
If Len(Line2) > 0 Then
PrintLine(File2, Line2)
End If
Loop
FileClose(File1, File2)
Console.WriteLine("Done")
Exit Sub
locError:
Console.WriteLine("Error: " & Err.Description)
End Sub
Function Strip(ByRef Text As String, ByRef Separator As String) As String
Dim nPos As Long
nPos = InStr(Text, Separator)
If nPos > 0 Then
Strip = Left$(Text, nPos - 1)
Text = Mid$(Text, nPos + Len(Separator))
Else
Strip = Text
Text = ""
End If
End Function
End Module
来源：https://stackoverflow.com/questions/11733076/how-do-i-robustly-parse-malformed-csv