summaryrefslogtreecommitdiff
path: root/report/viewer
diff options
context:
space:
mode:
authortrevor.cohn <trevor.cohn@ec762483-ff6d-05da-a07a-a48fb63a330f>2010-08-17 11:09:05 +0000
committertrevor.cohn <trevor.cohn@ec762483-ff6d-05da-a07a-a48fb63a330f>2010-08-17 11:09:05 +0000
commit59586b8b10f40b36178bd17f01497a73001cec5e (patch)
tree6e86880a64f31b131a776662cb1da1c97c5dfdf2 /report/viewer
parentf804499b85bee7ac5c37304412f8a3ae3da8f1e1 (diff)
Some more work on setup chapter. Nb. added some Chinese in UTF-8. Requires CJK package and the appropriate fonts to be installed. Tex-Live CJK does the trick.
git-svn-id: https://ws10smt.googlecode.com/svn/trunk@572 ec762483-ff6d-05da-a07a-a48fb63a330f
Diffstat (limited to 'report/viewer')
-rw-r--r--report/viewer/PMingLiU.ttfbin0 -> 19389344 bytes
-rw-r--r--report/viewer/alignment.py162
-rwxr-xr-xreport/viewer/display.py22
-rw-r--r--report/viewer/render.py128
4 files changed, 312 insertions, 0 deletions
diff --git a/report/viewer/PMingLiU.ttf b/report/viewer/PMingLiU.ttf
new file mode 100644
index 00000000..03e923bf
--- /dev/null
+++ b/report/viewer/PMingLiU.ttf
Binary files differ
diff --git a/report/viewer/alignment.py b/report/viewer/alignment.py
new file mode 100644
index 00000000..5fe03734
--- /dev/null
+++ b/report/viewer/alignment.py
@@ -0,0 +1,162 @@
+class Alignment:
+ SURE, POSSIBLE = 'S', 'P'
+
+ def __init__(self, swords, twords, align):
+ self.swords = swords
+ self.twords = twords
+ self.align = align
+
+ def reverse(self):
+ als = {}
+ for (frm, to), conf in self.align.items():
+ als[to, frm] = conf
+ return Alignment(self.twords, self.swords, als)
+
+ def merge(self, other):
+ assert self.swords == other.swords
+ assert self.twords == other.twords
+
+ als = {}
+ for frm, to in self.align.keys():
+ als[frm, to] = Alignment.POSSIBLE
+
+ for frm, to in other.align.keys():
+ if (frm, to) in als:
+ als[frm, to] = Alignment.SURE
+ else:
+ als[frm, to] = Alignment.POSSIBLE
+
+ return Alignment(self.swords, self.twords, als)
+
+ def __repr__(self):
+ return 'Alignment(swords=%s, twords=%s, align=%s)' % (self.swords, self.twords, self.align)
+
+def read_pharaoh_text(infile):
+ return infile.readline().strip().split()
+
+def parse_pharaoh_align(text):
+ als = {}
+ for part in text.strip().split():
+ frm, to = map(int, part.split('-'))
+ als[frm, to] = Alignment.SURE
+ return als
+
+def read_pharaoh_align(infile):
+ als = {}
+ for part in infile.readline().strip().split():
+ frm, to = map(int, part.split('-'))
+ als[frm, to] = Alignment.SURE
+ return als
+
+def read_pharaoh_alignment(swfile, twfile, afile):
+ sw = read_pharaoh_text(swfile)
+ tw = read_pharaoh_text(twfile)
+ als = read_pharaoh_align(afile)
+ return Alignment(sw, tw, als)
+
+def read_giza_alignment(infile):
+ infile.readline() # ignore
+ swords = infile.readline().strip().split()
+ twords = []
+ als = {}
+ state = 0
+ for token in infile.readline().strip().split():
+ if state == 0:
+ if token != 'NULL':
+ if token != '({':
+ twords.append(token)
+ else:
+ state = 1
+ elif state == 1:
+ if token != '})':
+ if twords:
+ als[int(token)-1, len(twords)-1] = Alignment.SURE
+ else:
+ state = 0
+ return Alignment(swords, twords, als)
+
+def read_naacl_aligns(infile):
+ aligns = []
+ last = None
+ for line in infile:
+ index, frm, to, conf = line.rstrip().split()
+ if int(index) != last:
+ aligns.append({})
+ aligns[-1][int(frm)-1, int(to)-1] = conf
+ last = int(index)
+ return aligns
+
+#
+# This phrase-extraction function largely mimics Pharaoh's phrase-extract
+# code. It also supports the option to not advance over NULL alignments.
+#
+
+def xextract_phrases(alignment, maxPhraseLength=None, advance=True):
+ T = len(alignment.twords)
+ S = len(alignment.swords)
+ if not maxPhraseLength:
+ maxPhraseLength = max(T, S)
+
+ alignedCountS = [0 for s in alignment.swords]
+ alignedToT = [[] for t in alignment.twords]
+ alignedToS = [[] for s in alignment.swords]
+ for (s, t), conf in alignment.align.items():
+ if conf == Alignment.SURE:
+ alignedCountS[s] += 1
+ alignedToT[t].append(s)
+ alignedToS[s].append(t)
+
+ # check alignments for english phrase startT...endT
+ for st in range(T):
+ for et in range(st, min(T, st + maxPhraseLength)):
+ minS = 9999
+ maxS = -1
+ usedS = alignedCountS[:]
+ for ti in range(st, et+1):
+ for si in alignedToT[ti]:
+ #print 'point (%d, %d)' % (si, ti)
+ if si<minS: minS = si
+ if si>maxS: maxS = si
+ usedS[si] -= 1
+
+ #print 's projected (%d-%d, %d, %d)' % (minS, maxS, st, et)
+ if (maxS >= 0 and # aligned to any foreign words at all
+ maxS-minS < maxPhraseLength): # foreign phrase within limits
+ # check if foreign words are aligned to out of bound english words
+ out_of_bounds = False
+ for si in range(minS, maxS):
+ if usedS[si] > 0:
+ #print 'out of bounds:', si
+ out_of_bounds = True
+ break
+
+ # Pharoah doesn't use this check, but I think it's required
+ if not out_of_bounds:
+ for s in range(minS, maxS+1):
+ for t in alignedToS[s]:
+ if not (st <= t <= et):
+ #print 'out of bounds2:', t,s
+ out_of_bounds = True
+ break
+
+ #print 'doing it for (%d-%d, %d, %d)' % (minS, maxS, st, et)
+ if not out_of_bounds:
+ if advance:
+ #print 'attempting to advance'
+ # start point of foreign phrase may advance over unaligned
+ ss = minS
+ while (ss>=0 and
+ ss>maxS-maxPhraseLength and # within length limit
+ (ss==minS or alignedCountS[ss]==0)): # unaligned
+ # end point of foreign phrase may advance over unaligned
+ es = maxS
+ while (es<S and
+ es<ss+maxPhraseLength and # within length limit
+ (es==maxS or alignedCountS[es]==0)): #unaligned
+ yield (ss, es, st, et)
+ es += 1
+ ss -= 1
+ else:
+ ss, es = minS, maxS
+ yield (minS, maxS, st, et)
+
diff --git a/report/viewer/display.py b/report/viewer/display.py
new file mode 100755
index 00000000..bf9d2a1f
--- /dev/null
+++ b/report/viewer/display.py
@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+
+import sys, os, gzip, re
+import render, alignment
+
+import reportlab.rl_config
+reportlab.rl_config.warnOnMissingFontGlyphs = 0
+from reportlab.pdfbase.ttfonts import TTFont
+from reportlab.pdfbase import pdfmetrics
+
+pdfmetrics.registerFont(TTFont('PMingLiU', 'PMingLiU.ttf'))
+
+doc = render.Document(sys.argv[1])
+
+for line in sys.stdin:
+ src, tgt, align = line.split(' ||| ')
+ src = src.split()
+ tgt = tgt.split()
+ align = alignment.parse_pharaoh_align(align)
+ doc.append(render.Alignment(src, tgt, align, 'PMingLiU', 'Helvetica', 8, 0.4))
+
+doc.render()
diff --git a/report/viewer/render.py b/report/viewer/render.py
new file mode 100644
index 00000000..0934c39c
--- /dev/null
+++ b/report/viewer/render.py
@@ -0,0 +1,128 @@
+from reportlab.pdfgen import canvas
+from reportlab.lib.colors import black, gray, white, magenta, Color
+from reportlab.lib.pagesizes import A4
+from reportlab.lib.styles import getSampleStyleSheet
+from reportlab.lib.units import cm, inch
+from reportlab.platypus import SimpleDocTemplate, Spacer, Paragraph
+from reportlab.platypus.flowables import Flowable
+import re
+
+class Alignment(Flowable):
+ def __init__(self, x_words, y_words, alignment, x_font, y_font, ptsize, unit, scale=True, colours=None):
+ self._x_words = x_words
+ self._y_words = y_words
+ self._alignment = alignment
+ self._unit = unit*cm
+ self._x_font = x_font
+ self._y_font = y_font
+ self._ptsize = ptsize
+ self._scale = 1
+ self._do_scale = scale
+ self._colours = colours
+ if not colours:
+ self._colours = {'S':black, 'P':gray, 'N':magenta}
+
+ def wrap(self, rw, rh):
+ xws = [self.canv.stringWidth(w, self._x_font, self._ptsize)
+ for w in self._x_words]
+ yws = [self.canv.stringWidth(w, self._y_font, self._ptsize)
+ for w in self._y_words]
+ width = (len(self._x_words) + 0.22)* self._unit + max(yws)
+ height = (len(self._y_words) + 0.22)* self._unit + max(xws)
+
+ if self._do_scale:
+ self._scale = min(rw / width, 1.5)
+ width *= self._scale
+ height *= self._scale
+
+ return (width, height)
+
+ def draw(self):
+ c = self.canv
+ print c.getAvailableFonts()
+
+ X=len(self._x_words)
+ Y=len(self._y_words)
+
+ c.saveState()
+ c.scale(self._scale, self._scale)
+
+ for (x, y), conf in self._alignment.items():
+ col = self._colours[conf]
+ if isinstance(col, Color):
+ c.setFillColor(col)
+ c.rect((0.02 + x)*self._unit, (0.02+Y-y-1)*self._unit,
+ self._unit, self._unit, 0, 1)
+ else:
+ bl = (x*self._unit, (Y-y-1)*self._unit)
+ tl = (x*self._unit, (Y-y)*self._unit)
+ tr = ((x+1)*self._unit, (Y-y)*self._unit)
+ br = ((x+1)*self._unit, (Y-y-1)*self._unit)
+
+ p = c.beginPath()
+ p.moveTo(*br)
+ p.lineTo(*tr)
+ p.lineTo(*tl)
+ c.setFillColor(col[0])
+ c.drawPath(p, fill=1)
+ p = c.beginPath()
+ p.moveTo(*br)
+ p.lineTo(*bl)
+ p.lineTo(*tl)
+ c.setFillColor(col[1])
+ c.drawPath(p, fill=1)
+
+ c.setStrokeColor(black)
+ c.grid(map(lambda x: (0.02+x)*self._unit, range(X+1)),
+ map(lambda y: (0.02+y)*self._unit, range(Y+1)))
+
+ c.setFont(self._x_font, self._ptsize)
+ c.setFillColor(black)
+ for x, word in enumerate(self._x_words):
+ c.saveState()
+ c.translate((x+0.52)*self._unit, (Y+0.22)*self._unit)
+ c.rotate(60)
+ c.drawString(0, 0, word)
+ c.restoreState()
+
+ c.setFont(self._y_font, self._ptsize)
+ for y, word in enumerate(self._y_words):
+ c.drawString((X+0.22)*self._unit, (Y-y+0.42-1)*self._unit, word)
+
+ c.restoreState()
+
+class Document:
+ def __init__(self, filename):
+ self._styles = getSampleStyleSheet()
+ self._doc = SimpleDocTemplate(filename)
+ self._story = []
+
+ def append(self, flowable):
+ self._story.append(flowable)
+ self._story.append(Spacer(1, 1*cm))
+
+ def render(self):
+ self._doc.build(self._story[:-1])
+
+class Canvas:
+ def __init__(self, filename):
+ self._filename = filename
+ self._canvas = canvas.Canvas('.' + filename, A4)
+ self._size = A4
+ self._body = None
+
+ def append(self, flowable):
+ if self._body:
+ print >>sys.stderr, 'WARNING: replacing existing flowable'
+ self._body = flowable
+
+ def render(self):
+ self._body.canv = self._canvas
+ width, height = self._body.wrap(*self._size)
+ width *= 1.02
+ height *= 1.02
+
+ self._canvas = canvas.Canvas(self._filename, (width, height))
+ self._body.canv = self._canvas
+ self._body.draw()
+ self._canvas.save()