OrgGo/unipdf
1
0
Fork 0
mirror of https://github.com/unidoc/unipdf.git synced 2025-05-05 19:30:30 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Fix numeric parsing bug when only a single number. Added testcase.

Browse Source
This commit is contained in:
Gunnsteinn Hall 2019-03-14 01:07:32 +00:00
parent 0686b01fa9
commit 443b168e48
3 changed files with 48 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
pdf/core/crossrefs.go
View File

@ -85,7 +85,7 @@ func (parser *PdfParser) lookupObjectViaOS(sobjNumber int, objNum int) (PdfObjec
} }
sod := so.PdfObjectDictionary sod := so.PdfObjectDictionary
common.Log.Trace("so d: %s\n", *sod) common.Log.Trace("so d: %s\n", sod.String())
name, ok := sod.Get("Type").(*PdfObjectName) name, ok := sod.Get("Type").(*PdfObjectName)
if !ok { if !ok {
common.Log.Debug("ERROR: Object stream should always have a Type") common.Log.Debug("ERROR: Object stream should always have a Type")

9
pdf/core/parser.go
View File

@ -526,7 +526,14 @@ func (parser *PdfParser) parseObject() (PdfObject, error) {
for { for {
bb, err := parser.reader.Peek(2) bb, err := parser.reader.Peek(2)
if err != nil { if err != nil {
return nil, err // If EOFs after 1 byte then should still try to continue parsing.
if err != io.EOF || len(bb) == 0 {
return nil, err
}
if len(bb) == 1 {
// Add space as code below is expecting 2 bytes.
bb = append(bb, ' ')
}
} }
common.Log.Trace("Peek string: %s", string(bb)) common.Log.Trace("Peek string: %s", string(bb))

59
pdf/core/parser_test.go
View File

@ -44,16 +44,16 @@ var namePairs = map[string]string{
"/Name1": "Name1", "/Name1": "Name1",
"/ASomewhatLongerName": "ASomewhatLongerName", "/ASomewhatLongerName": "ASomewhatLongerName",
"/A;Name_With-Various***Characters?": "A;Name_With-Various***Characters?", "/A;Name_With-Various***Characters?": "A;Name_With-Various***Characters?",
"/1.2": "1.2", "/1.2": "1.2",
"/$$": "$$", "/$$": "$$",
"/@pattern": "@pattern", "/@pattern": "@pattern",
"/.notdef": ".notdef", "/.notdef": ".notdef",
"/Lime#20Green": "Lime Green", "/Lime#20Green": "Lime Green",
"/paired#28#29parentheses": "paired()parentheses", "/paired#28#29parentheses": "paired()parentheses",
"/The_Key_of_F#23_Minor": "The_Key_of_F#_Minor", "/The_Key_of_F#23_Minor": "The_Key_of_F#_Minor",
"/A#42": "AB", "/A#42": "AB",
"/": "", "/": "",
"/ ": "", "/ ": "",
"/#3CBC88#3E#3CC5ED#3E#3CD544#3E#3CC694#3E": "<BC88><C5ED><D544><C694>", "/#3CBC88#3E#3CC5ED#3E#3CD544#3E#3CC694#3E": "<BC88><C5ED><D544><C694>",
} }
@ -105,18 +105,18 @@ func BenchmarkStringParsing(b *testing.B) {
} }
var stringPairs = map[string]string{ var stringPairs = map[string]string{
"(This is a string)": "This is a string", "(This is a string)": "This is a string",
"(Strings may contain\n newlines and such)": "Strings may contain\n newlines and such", "(Strings may contain\n newlines and such)": "Strings may contain\n newlines and such",
"(Strings may contain balanced parenthesis () and\nspecial characters (*!&}^% and so on).)": "Strings may contain balanced parenthesis () and\nspecial characters (*!&}^% and so on).", "(Strings may contain balanced parenthesis () and\nspecial characters (*!&}^% and so on).)": "Strings may contain balanced parenthesis () and\nspecial characters (*!&}^% and so on).",
"(These \\\ntwo strings \\\nare the same.)": "These two strings are the same.", "(These \\\ntwo strings \\\nare the same.)": "These two strings are the same.",
"(These two strings are the same.)": "These two strings are the same.", "(These two strings are the same.)": "These two strings are the same.",
"(\\\\)": "\\", "(\\\\)": "\\",
"(This string has an end-of-line at the end of it.\n)": "This string has an end-of-line at the end of it.\n", "(This string has an end-of-line at the end of it.\n)": "This string has an end-of-line at the end of it.\n",
"(So does this one.\\n)": "So does this one.\n", "(So does this one.\\n)": "So does this one.\n",
"(\\0053)": "\0053", "(\\0053)": "\0053",
"(\\53)": "\053", "(\\53)": "\053",
"(\\053)": "+", "(\\053)": "+",
"(\\53\\101)": "+A", "(\\53\\101)": "+A",
} }
func TestStringParsing(t *testing.T) { func TestStringParsing(t *testing.T) {
@ -588,6 +588,7 @@ endobj`
common.Log.Debug("Xref dict: %s", xrefDict) common.Log.Debug("Xref dict: %s", xrefDict)
} }
// TODO(gunnsth): Clear up. Should define clear inputs and expectation data and then run it.
func TestObjectParse(t *testing.T) { func TestObjectParse(t *testing.T) {
parser := PdfParser{} parser := PdfParser{}
@ -601,6 +602,24 @@ func TestObjectParse(t *testing.T) {
return return
} }
// Integer
rawText = "0"
parser.rs, parser.reader, parser.fileSize = makeReaderForText(rawText)
obj, err = parser.parseObject()
if err != nil {
t.Errorf("Error parsing object: %v", err)
return
}
nump, ok := obj.(*PdfObjectInteger)
if !ok {
t.Errorf("Unable to identify integer")
return
}
if *nump != 0 {
t.Errorf("Wrong value, expecting 9 (%d)", *nump)
return
}
// Integer // Integer
rawText = "9 0 false" rawText = "9 0 false"
parser.rs, parser.reader, parser.fileSize = makeReaderForText(rawText) parser.rs, parser.reader, parser.fileSize = makeReaderForText(rawText)
@ -610,7 +629,7 @@ func TestObjectParse(t *testing.T) {
t.Errorf("Error parsing object") t.Errorf("Error parsing object")
return return
} }
nump, ok := obj.(*PdfObjectInteger) nump, ok = obj.(*PdfObjectInteger)
if !ok { if !ok {
t.Errorf("Unable to identify integer") t.Errorf("Unable to identify integer")
return return