Added Block, PdfReader, Range and TextPatterns.

NanScan/Block.py

@@ -0,0 +1,92 @@
+#   Copyright (C) 2009 by Albert Cervera i Areny
+#   albert@nan-tic.com
+#
+#   This program is free software; you can redistribute it and/or modify 
+#   it under the terms of the GNU General Public License as published by
+#   the Free Software Foundation; either version 2 of the License, or 
+#   (at your option) any later version. 
+#
+#   This program is distributed in the hope that it will be useful, 
+#   but WITHOUT ANY WARRANTY; without even the implied warranty of 
+#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the 
+#   GNU General Public License for more details.
+#
+#   You should have received a copy of the GNU General Public License 
+#   along with this program; if not, write to the
+#   Free Software Foundation, Inc.,
+#   59 Temple Place - Suite 330, Boston, MA  02111-1307, USA. 
+
+
+from PyQt4.QtCore import *
+
+def blockDistanceComparison(x, y):
+	if x.distance > y.distance:
+		return 1
+	elif x.distance < y.distance:
+		return -1
+	else:
+		return 0
+
+def blockSizeComparison(x, y):
+	xRect = x.rect()
+	yRect = y.rect()
+	xt = len( xRect.width() * xRect.height() )
+	yt = len( yRect.width() * yRect.height() )
+	if xt > yt:
+		return 1
+	elif xt < yt:
+		return -1
+	else:
+		return 0
+
+## @brief This class represents a group of characters in a document.
+class Block:
+	def __init__(self):
+		self.document = None
+		self.boxes = []
+		self.outerDistane = 10
+
+	## @brief Returns a unicode string with the text of the current range
+	def text(self):
+		line = self.document[self.line]
+		chars = line[self.pos:self.pos + self.length]
+		return u''.join( [x.character for x in chars] )
+
+	## @brief Returns the bounding rectangle of the text in the range
+	def rect(self):
+		rect = QRectF()
+		for c in self.boxes:
+			rect = rect.united( c.box )
+		return rect
+
+	## @brief Returns a bounding rectangle of the text in the block that is 'outerDistance'
+	# larger in all sides.
+	def outerRect(self):
+		rect = self.rect()
+		rect.translate( - self.outerDistance, - self.outerDistance )
+		rect.setWidth( rect.width() + self.outerDistance * 2 )
+		rect.setHeight( rect.height() + self.outerDistance * 2 )
+		return rect
+
+	## @brief Returns a list with all possible ranges of size length of the 
+	# given document
+	@staticmethod
+	def extractAllBlocksFromDocument(lines, length, distance=0):
+		if length <= 0:
+			return []
+		blocks = []
+		for line in xrange(len(lines)):
+			for char in xrange(len(line)):
+				blockFound = False
+				for block in blocks:
+					if block.outerRect().intersects( char.box ):
+						block.boxes.append( char )
+						blockFound = True
+						break
+				if not blockFound:
+					block = Block()
+					block.boxes.append( char )
+					block.document = lines
+					blocks.append( block )
+		return blocks
+

NanScan/PdfReader.py

@@ -0,0 +1,16 @@
+import poppler
+
+document = poppler.document_new_from_file ('file:///home/albert/prog/empresa/info/pla-empresa/empresa.pdf', None)
+#self.document = poppler.document_new_from_file (uri, None)
+print "PAGES: ", document.get_n_pages()
+print "SIZE: ", current_page.get_size()
+
+
+# Font Info:
+font_info = poppler.FontInfo(self.document)
+iter = font_info.scan(self.n_pages)
+
+print iter.get_full_name()
+
+while iter.next():
+    print iter.get_full_name()

NanScan/Range.py

@@ -0,0 +1,93 @@
+#   Copyright (C) 2009 by Albert Cervera i Areny
+#   albert@nan-tic.com
+#
+#   This program is free software; you can redistribute it and/or modify 
+#   it under the terms of the GNU General Public License as published by
+#   the Free Software Foundation; either version 2 of the License, or 
+#   (at your option) any later version. 
+#
+#   This program is distributed in the hope that it will be useful, 
+#   but WITHOUT ANY WARRANTY; without even the implied warranty of 
+#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the 
+#   GNU General Public License for more details.
+#
+#   You should have received a copy of the GNU General Public License 
+#   along with this program; if not, write to the
+#   Free Software Foundation, Inc.,
+#   59 Temple Place - Suite 330, Boston, MA  02111-1307, USA. 
+
+
+from PyQt4.QtCore import *
+
+def rangeDistanceComparison(x, y):
+	if x.distance > y.distance:
+		return 1
+	elif x.distance < y.distance:
+		return -1
+	else:
+		return 0
+
+def rangeLengthComparison(x, y):
+	xt = len( x.text() )
+	yt = len( y.text() )
+	if xt > yt:
+		return 1
+	elif xt < yt:
+		return -1
+	else:
+		return 0
+
+## @brief This class represents a group of characters in a document.
+class Range:
+	def __init__(self):
+		self.line = 0
+		self.pos = 0
+		self.length = 0
+		self.document = None
+
+	## @brief Returns a unicode string with the text of the current range
+	def text(self):
+		line = self.document[self.line]
+		chars = line[self.pos:self.pos + self.length]
+		return u''.join( [x.character for x in chars] )
+
+	## @brief Returns the bounding rectangle of the text in the range
+	def rect(self):
+		line = self.document[self.line]
+		chars = line[self.pos:self.pos + self.length]
+		rect = QRectF()
+		for c in chars:
+			rect = rect.united( c.box )
+		return rect
+
+	## @brief Returns a list with all possible ranges of size length of the 
+	# given document
+	@staticmethod
+	def extractAllRangesFromDocument(lines, length, width=0):
+		if length <= 0:
+			return []
+		ranges = []
+		for line in xrange(len(lines)):
+			if length >= len(lines[line]):
+				ran = Range()
+				ran.line = line
+				ran.pos = 0
+				ran.length = len(lines[line])
+				ran.document = lines
+				#if width:
+				#	while ran.rect().width() > width:
+				#		ran.length -= 1
+				ranges.append( ran )
+				continue
+			for pos in xrange(len(lines[line]) - length + 1):
+				ran = Range()
+				ran.line = line
+				ran.pos = pos
+				ran.length = length
+				ran.document = lines
+				#if width:
+				#	while ran.rect().width() > width:
+				#		ran.length -= 1
+				ranges.append( ran )
+		return ranges
+

NanScan/TextPatterns.py

@@ -0,0 +1,63 @@
+#   Copyright (C) 2009 by Albert Cervera i Areny
+#   albert@nan-tic.com
+#
+#   This program is free software; you can redistribute it and/or modify 
+#   it under the terms of the GNU General Public License as published by
+#   the Free Software Foundation; either version 2 of the License, or 
+#   (at your option) any later version. 
+#
+#   This program is distributed in the hope that it will be useful, 
+#   but WITHOUT ANY WARRANTY; without even the implied warranty of 
+#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the 
+#   GNU General Public License for more details.
+#
+#   You should have received a copy of the GNU General Public License 
+#   along with this program; if not, write to the
+#   Free Software Foundation, Inc.,
+#   59 Temple Place - Suite 330, Boston, MA  02111-1307, USA. 
+
+from PyQt4.QtCore import *
+
+def textToFloat( value ):
+	if ',' in value and '.' in value:
+		commaIndex = value.rfind(',')
+		periodIndex = value.rfind('.')
+		if commaIndex > periodIndex:
+			newValue = value.replace( '.', '' ).replace( ',', '.' )
+		else:
+			newValue = value.replace( ',', '' )
+	elif ',' in value:
+		newValue = value.replace( ',', '.' )
+	else:
+		newValue = value
+	return float( newValue )
+
+def isFloat( value ):
+	try:
+		textToFloat( value )
+		return True
+	except:
+		return False
+
+def isDate( value ):
+	date = textToDate( value )
+	return date.isValid()
+
+def textToDate( value ):
+	patterns = ['dd/MM/yyyy', 'dd-MM-yyyy', 'dd-MM-yy', 'dd MMM. yy', 'dd MMMM yyyy', 'dd.mm.yyyy']
+	for pattern in patterns:
+		date = QDate.fromString( value.replace(' ',''), pattern )
+		if date.isValid():
+			return date
+	return QDate()
+
+def isMostlyNumeric( text ):
+	numbers = 0
+	for x in text:
+		if x in '0123456789':
+			numbers += 1
+	if numbers > len(text) / 2:
+		return True
+	else:
+		return False
+