test cases updated

git-svn-id: https://pdfminerr.googlecode.com/svn/trunk/pdfminer@282 1aa58f4a-7d42-0410-adbc-911cccaed67c

samples/Makefile

@@ -5,7 +5,7 @@ RM=rm -f
 CMP=:
 PYTHON=python2
 
-PDF2TXT=PYTHONPATH=.. $(PYTHON) ../tools/pdf2txt.py -Dx -p1
+PDF2TXT=PYTHONPATH=.. $(PYTHON) ../tools/pdf2txt.py -p1
 
 HTMLS=$(HTMLS_FREE) $(HTMLS_NONFREE)
 HTMLS_FREE= \
@@ -49,8 +49,7 @@ XMLS_NONFREE= \
 	nonfree/naacl06-shinyama.xml \
 	nonfree/nlp2004slides.xml
 
-all:
+all: test
-	$(MAKE) test CMP=cmp
 
 test: htmls texts xmls
 

samples/nonfree/dmca.txt.ref

@@ -14,6 +14,16 @@ number of other significant copyright-related issues.
 
 The DMCA is divided into five titles:  
 
+!
+
+!
+
+!
+
+!
+
+!
+
 Title I, the “WIPO Copyright and Performances and Phonograms
 Treaties  Implementation  Act  of  1998,”  implements  the  WIPO
 treaties.
@@ -32,16 +42,6 @@ of rights in motion pictures.
 Title V, the “Vessel Hull Design Protection Act,” creates a new form
 of protection for the design of vessel hulls.
 
-!
-
-!
-
-!
-
-!
-
-!
-
 This memorandum summarizes briefly each  title of  the DMCA.   It provides
 merely  an overview of  the  law’s provisions;  for purposes of  length  and  readability  a
 significant  amount of detail has been omitted.   A  complete understanding of  any

samples/nonfree/dmca.xml.ref

@@ -568,7 +568,42 @@
 </text>
 </textline>
 </textbox>
-<textbox id="5" bbox="180.000,235.452,504.108,464.124">
+<textbox id="5" bbox="144.000,450.000,152.004,462.480">
+<textline bbox="144.000,450.000,152.004,462.480">
+<text font="ELCKGH+WPTypographicSymbols" bbox="144.000,450.000,152.004,462.480" size="12.480">!</text>
+<text>
+</text>
+</textline>
+</textbox>
+<textbox id="6" bbox="144.000,409.680,152.004,422.160">
+<textline bbox="144.000,409.680,152.004,422.160">
+<text font="ELCKGH+WPTypographicSymbols" bbox="144.000,409.680,152.004,422.160" size="12.480">!</text>
+<text>
+</text>
+</textline>
+</textbox>
+<textbox id="7" bbox="144.000,369.360,152.004,381.840">
+<textline bbox="144.000,369.360,152.004,381.840">
+<text font="ELCKGH+WPTypographicSymbols" bbox="144.000,369.360,152.004,381.840" size="12.480">!</text>
+<text>
+</text>
+</textline>
+</textbox>
+<textbox id="8" bbox="144.000,329.040,152.004,341.520">
+<textline bbox="144.000,329.040,152.004,341.520">
+<text font="ELCKGH+WPTypographicSymbols" bbox="144.000,329.040,152.004,341.520" size="12.480">!</text>
+<text>
+</text>
+</textline>
+</textbox>
+<textbox id="9" bbox="144.000,248.400,152.004,260.880">
+<textline bbox="144.000,248.400,152.004,260.880">
+<text font="ELCKGH+WPTypographicSymbols" bbox="144.000,248.400,152.004,260.880" size="12.480">!</text>
+<text>
+</text>
+</textline>
+</textbox>
+<textbox id="10" bbox="180.000,235.452,504.108,464.124">
 <textline bbox="180.000,450.492,503.985,464.124">
 <text font="Garamond" bbox="180.000,450.492,187.380,464.064" size="13.572">T</text>
 <text font="Garamond" bbox="187.440,450.492,190.188,464.064" size="13.572">i</text>
@@ -1669,41 +1704,6 @@
 </text>
 </textline>
 </textbox>
-<textbox id="6" bbox="144.000,450.000,152.004,462.480">
-<textline bbox="144.000,450.000,152.004,462.480">
-<text font="ELCKGH+WPTypographicSymbols" bbox="144.000,450.000,152.004,462.480" size="12.480">!</text>
-<text>
-</text>
-</textline>
-</textbox>
-<textbox id="7" bbox="144.000,409.680,152.004,422.160">
-<textline bbox="144.000,409.680,152.004,422.160">
-<text font="ELCKGH+WPTypographicSymbols" bbox="144.000,409.680,152.004,422.160" size="12.480">!</text>
-<text>
-</text>
-</textline>
-</textbox>
-<textbox id="8" bbox="144.000,369.360,152.004,381.840">
-<textline bbox="144.000,369.360,152.004,381.840">
-<text font="ELCKGH+WPTypographicSymbols" bbox="144.000,369.360,152.004,381.840" size="12.480">!</text>
-<text>
-</text>
-</textline>
-</textbox>
-<textbox id="9" bbox="144.000,329.040,152.004,341.520">
-<textline bbox="144.000,329.040,152.004,341.520">
-<text font="ELCKGH+WPTypographicSymbols" bbox="144.000,329.040,152.004,341.520" size="12.480">!</text>
-<text>
-</text>
-</textline>
-</textbox>
-<textbox id="10" bbox="144.000,248.400,152.004,260.880">
-<textline bbox="144.000,248.400,152.004,260.880">
-<text font="ELCKGH+WPTypographicSymbols" bbox="144.000,248.400,152.004,260.880" size="12.480">!</text>
-<text>
-</text>
-</textline>
-</textbox>
 <textbox id="11" bbox="108.000,168.360,504.108,222.144">
 <textline bbox="144.000,208.572,504.060,222.144">
 <text font="Garamond" bbox="144.000,208.572,151.380,222.144" size="13.572">T</text>
@@ -2194,20 +2194,20 @@
 <textgroup bbox="144.000,235.452,504.108,490.944">
 <textbox id="4" bbox="144.000,477.372,323.881,490.944" />
 <textgroup bbox="144.000,235.452,504.108,464.124">
-<textbox id="5" bbox="180.000,235.452,504.108,464.124" />
 <textgroup bbox="144.000,248.400,152.004,462.480">
 <textgroup bbox="144.000,329.040,152.004,462.480">
 <textgroup bbox="144.000,369.360,152.004,462.480">
 <textgroup bbox="144.000,409.680,152.004,462.480">
-<textbox id="6" bbox="144.000,450.000,152.004,462.480" />
+<textbox id="5" bbox="144.000,450.000,152.004,462.480" />
-<textbox id="7" bbox="144.000,409.680,152.004,422.160" />
+<textbox id="6" bbox="144.000,409.680,152.004,422.160" />
 </textgroup>
-<textbox id="8" bbox="144.000,369.360,152.004,381.840" />
+<textbox id="7" bbox="144.000,369.360,152.004,381.840" />
 </textgroup>
-<textbox id="9" bbox="144.000,329.040,152.004,341.520" />
+<textbox id="8" bbox="144.000,329.040,152.004,341.520" />
 </textgroup>
-<textbox id="10" bbox="144.000,248.400,152.004,260.880" />
+<textbox id="9" bbox="144.000,248.400,152.004,260.880" />
 </textgroup>
+<textbox id="10" bbox="180.000,235.452,504.108,464.124" />
 </textgroup>
 </textgroup>
 <textbox id="11" bbox="108.000,168.360,504.108,222.144" />

samples/nonfree/f1040nr.txt.ref

@@ -6,7 +6,7 @@ OMB No.  1545-0074
 Identifying  number  (see  page  8)
  
 
-I  
+ I
 
 Check  if:
  
@@ -18,11 +18,11 @@ Type  of  entry  visa  (see  page  8)
 
 䊳  
 
-7  a
+7a 
 Yourself
  
 
-7  b
+7b 
 Spouse
  
 
@@ -45,10 +45,8 @@ on  7a  and  7b
 No.  of  children  on
 7c who:
  
-lived with  you
+● lived with  you
-●
+ ● did not live with
- 
-● did not live with
 you due to divorce 
 or separation
  
@@ -60,14 +58,13 @@ on  lines  above
  
 8
  
-9  a
+9a 
 
  A
 
 1040NR
  
 Form 
- 
 Department  of  the  Treasury
 beginning
 Internal  Revenue  Service
@@ -92,8 +89,8 @@ Country 䊳
 Of what  country were  you  a citizen or  national  during  the  tax  year? 䊳
  
  
-Give  address outside  the United  States to which  you want  any
 Give  address  in  the  country where  you  are  a permanent  resident.
+Give  address outside  the United  States to which  you want  any
 refund  check mailed.  If  same  as  above, write  “Same.”
 If  same  as  above, write  “Same.”
  
@@ -103,12 +100,12 @@ If  same  as  above, write  “Same.”
 
  
 
-.epyt  ro  tnirp  esaelP
+Please print or type.
 
  
 
-.dlehhtiw  saw  xat  fi  R-9901  )s(mroF  hcatta  oslA
+Also attach Form(s) 1099-R if tax was withheld.
-.ereh  2-W  smroF  hcattA
+Attach Forms W-2 here.
 
  
 
@@ -128,6 +125,10 @@ child  for  child  tax
 credit  (see  page  9)
  
 
+ 
+
+ 
+
 其 
 
 Filing  Status  and  Exemptions  for  Individuals (see  page  8)
@@ -160,14 +161,10 @@ Qualifying widow(er) with  dependent  child  (see  page  9)
 Caution: Do  not check  box  7a  if  your  parent  (or  someone  else)  can  claim  you  as  a  dependent.
 Do  not check  box  7b  if  your  spouse  had  any U.S.  gross  income.
  
-7  c
+7c 
 Dependents:  (see  page  9)
  
 
- 
-
- 
-
 (1)  First  name
  
 
@@ -212,25 +209,22 @@ identifying  number
 
 10a 
 
-
+11 
-1  1
+12 
-1  2
+13 
-1  3
+14 
-1  4
+15 
-1  5
 16b 
- 
 17b 
+18 
+19 
+20 
+21 
 
-1  8
+23 
-1  9
-2  0
-2  1
 
-2  3
+34 
-
+35 
-3  4
-3  5
 
 d
  
@@ -245,23 +239,7 @@ d
 
   
 
-  
+9b 
-
-䊳  
-
-9  b
-
-䊳  
-
-8
- 
-9  a
-b
- 
-10a
- 
-b
- 
 
 Total  number  of  exemptions  claimed
  
@@ -273,22 +251,21 @@ Tax-exempt interest.  Do  not  include  on  line  9a
 Ordinary  dividends
 10b 
  
- 
 Qualified  dividends  (see  page  11) 
  
-1  1
+11 
 Taxable  refunds,  credits,  or  offsets  of  state  and  local  income  taxes  (see  page  11) 
  
-1  2
+12 
 Scholarship  and  fellowship  grants.  Attach  Form(s)  1042-S  or  required  statement  (see  page  11) 
  
-1  3
+13 
 Business  income  or  (loss).  Attach  Schedule C  or C-EZ  (Form  1040)
  
-1  4
+14 
 Capital  gain  or  (loss).  Attach  Schedule D  (Form  1040)  if  required.  If  not  required,  check  here
  
-1  5
+15 
 Other  gains  or  (losses).  Attach  Form  4797
 16a
 16b 
@@ -296,8 +273,6 @@ Other  gains  or  (losses).  Attach  Form  4797
 Taxable  amount  (see  page  12)
 IRA  distributions
  
- 
- 
 17a
  
  
@@ -308,77 +283,88 @@ Pensions  and  annuities
  
  
  
- 
+18 
- 
-1  8
 Rental  real  estate,  royalties,  partnerships,  trusts,  etc.  Attach  Schedule  E  (Form  1040)
-1  9
+19 
 Farm  income  or  (loss).  Attach  Schedule  F  (Form  1040)
  
-2  0
+20 
 Unemployment  compensation
  
-2  1
+21 
 Other  income.  List  type  and  amount  (see  page  15)
-2  2
+22 
-2  2
+22 
 Total  income  exempt  by  a  treaty  from  page  5,  Item M
  
-2  3
+23 
-Add  lines  8,  9a,  10a,  11–15,  16b,  and  17b–21.  This  is  your total  effectively  connected  income
+Add  lines  8,  9a,  10a,  11–15,  16b,  and  17b–21.  This  is  your total  effectively  connected  income 䊳
  
-2  4
+ 
-2  4
+24 
+24 
 Educator  expenses  (see  page  15)
-2  5
+25 
-2  5
+25 
 Health  savings  account  deduction.  Attach  Form  8889
-2  6
+26 
-2  6
+26 
 Moving  expenses.  Attach  Form  3903
-2  7
+27 
  
-2  7
+27 
 Self-employed  SEP,  SIMPLE,  and  qualified  plans
-2  8
+28 
  
-2  8
+28 
 Self-employed  health  insurance  deduction  (see  page  16) 
-2  9
+29 
-2  9
+29 
 Penalty  on  early withdrawal  of  savings
-3  0
+30 
  
-3  0
+30 
 Scholarship  and  fellowship  grants  excluded
-3  1
+31 
  
 IRA  deduction  (see  page  16)
-3  1
+31 
-3  2
+32 
  
-3  2
+32 
 Student  loan  interest  deduction  (see  page  16)
-3  3
+33 
  
-3  3
+33 
 Domestic  production  activities  deduction.  Attach  Form  8903
  
-3  4
+34 
 Add  lines  24  through  33
-3  5
+35 
-Subtract  line  34  from  line  23.  Enter  here  and  on  line  36.  This  is  your adjusted  gross  income
+Subtract  line  34  from  line  23.  Enter  here  and  on  line  36.  This  is  your adjusted  gross  income 䊳
+ 
  
 For Disclosure,  Privacy  Act,  and  Paperwork Reduction  Act Notice,  see  page  32.
 Cat. No.  11364D
  
  
 
-ssenisuB/edarT  .S.U  htiW  detcennoC  ylevitceffE  emocnI
+Income Effectively Connected With U.S. Trade/Business
+
+Enclose, but do not attach, any payment.
+
+8
+ 
+9a 
+b
+ 
+10a 
+b
+ 
+
+Adjusted Gross Income
 
-.tnemyap  yna  ,hcatta  ton  od  tub  ,esolcnE
  
-emocnI  ssorG  detsujdA
 
  
 

samples/nonfree/i1040nr.txt.ref

@@ -1,19 +1,11 @@
+Leadpct: 0% Pt. size: 9.5 ❏ Draft
+Userid: ________ DTD INSTR04
 PAGER/SGML
-Page 1 of 48
-
-________
-
-Leadpct: 0%
-
-DTD INSTR04
-
-Pt. size: 9.5 ❏ Draft
-Userid:
 (Init. & date)
 Fileid:
 D:\USERS\8fllb\documents\epicfiles\2007Instructions1040NR.sgm
+Page 1 of 48 Instructions for Form 1040NR
 7:48 -  6-DEC-2007
-Instructions for Form 1040NR
 
 ❏ Ok to Print
 
@@ -27,6 +19,122 @@ U.S. Nonresident Alien  Income Tax Return
 Department of the Treasury
 Internal Revenue Service
 
+use a different address this year. See
+Section references are to the Internal
+Where To File on page 4.
+Revenue Code unless otherwise noted.
+General Instructions deduction. The deduction rate for
+Domestic production activities
+2007 is increased to 6%.
+What’s New for 2007
+Unreported social security and
+Medicare tax on wages.
+ If you are
+Tax benefits extended. The following
+an employee and your employer did not
+tax benefits were extended through
+withhold social security and Medicare
+2007.
+• Deduction for educator expenses in
+tax, see Form 8919 to figure and report
+this tax.
+figuring adjusted gross income.
+• District of Columbia first-time
+Refundable credit for prior-year
+minimum tax.
+If you have an unused
+homebuyer credit.
+minimum tax credit carryforward from
+Alternative minimum tax (AMT)
+2004, see Form 8801 to find if you can
+exemption amount decreased. The
+take this credit.
+AMT exemption amount is decreased to
+Health savings account (HSA)
+$33,750 ($45,000 if a qualifying
+funding distributions. You may be
+widow(er); $22,500 if married filing
+able to elect to exclude from income a
+separately).
+distribution made from your IRA to your
+At the time these instructions
+HSA. See the instructions for lines 16a
+!
+went to print, Congress was
+and 16b beginning on page 12.
+considering legislation that
+CAUTION
+New recordkeeping requirements for
+would increase the amounts above. To
+contributions of money.
+ For
+find out if this legislation was enacted,
+charitable contributions of money,
+and for more details, see the
+regardless of the amount, you must
+Instructions for Form 6251.
+maintain as a record of the contribution
+IRA deduction expanded.
+If you were
+a bank record (such as a cancelled
+covered by a retirement plan, you may
+check) or a written record from the
+be able to take an IRA deduction if your
+charity. The written record must include
+2007 modified adjusted gross income
+the name of the charity, date, and
+(AGI) is less than $62,000 ($103,000 if
+amount of the contribution. See Gifts to
+a qualifying widow(er)).
+U.S. Charities that begins on page 26.
+You may be able to deduct up to an
+Exemption for housing a person
+additional $3,000 if you were a
+displaced by Hurricane Katrina
+participant in a 401(k) plan and your
+expires. The additional exemption
+employer was in bankruptcy in an
+amount for housing a person displaced
+earlier year.
+by Hurricane Katrina does not apply for
+2007 or later years.
+Standard mileage rates. The 2007
+Telephone excise tax credit.
+rate for business use of your vehicle is
+ This
+481/2 cents a mile. The 2007 rate for
+credit was available only on your 2006
+use of your vehicle to move is 20 cents
+return. If you filed but did not request it
+a mile. The special rate for charitable
+on your 2006 return, file Form 1040X
+use of your vehicle to provide relief
+using a simplified procedure explained
+related to Hurricane Katrina has
+in its instructions to amend your 2006
+expired.
+return. If you were not required to file a
+2006 return, see the 2006 Form
+Elective salary deferrals. The
+1040EZ-T.
+maximum amount you can defer under
+all plans is generally limited to $15,500
+What’s New for 2008
+($10,500 if you only have SIMPLE
+plans; $18,500 for section 403(b) plans
+IRA deduction expanded. You may
+if you qualify for the 15-year rule). See
+be able to deduct up to $5,000 ($6,000
+the instructions for line 8 on page 10.
+if age 50 or older at the end of the
+Mailing your return.
+ If you are filing
+year). You may be able to take an IRA
+deduction if you were covered by a
+the return for an estate or trust, you will
+
+Cat. No. 11368V
+
 retirement plan and your 2008 modified
 AGI is less than $63,000 ($105,000) if a
 qualifying widow(er)).
@@ -71,8 +179,7 @@ investment income on a parent’s return
 and the special rule for when a child
 must file Form 6251 will also apply to
 the children listed above.
-Expiring tax benefits.
+Expiring tax benefits. The following
-The following
 benefits are scheduled to expire and
 will not apply for 2008.
 • Deduction for educator expenses in
@@ -85,130 +192,4 @@ property.
 homebuyer credit (for homes
 purchased after 2007).
 
-Section references are to the Internal
-Revenue Code unless otherwise noted.
-General Instructions
-What’s New for 2007
-Tax benefits extended.
-The following
-tax benefits were extended through
-2007.
-• Deduction for educator expenses in
-figuring adjusted gross income.
-• District of Columbia first-time
-homebuyer credit.
-Alternative minimum tax (AMT)
-exemption amount decreased.
-The
-AMT exemption amount is decreased to
-$33,750 ($45,000 if a qualifying
-widow(er); $22,500 if married filing
-separately).
-At the time these instructions
-!
-went to print, Congress was
-considering legislation that
-CAUTION
-would increase the amounts above. To
-find out if this legislation was enacted,
-and for more details, see the
-Instructions for Form 6251.
-IRA deduction expanded.
-If you were
-covered by a retirement plan, you may
-be able to take an IRA deduction if your
-2007 modified adjusted gross income
-(AGI) is less than $62,000 ($103,000 if
-a qualifying widow(er)).
-You may be able to deduct up to an
-additional $3,000 if you were a
-participant in a 401(k) plan and your
-employer was in bankruptcy in an
-earlier year.
-Standard mileage rates.
-The 2007
-rate for business use of your vehicle is
-481/2 cents a mile. The 2007 rate for
-use of your vehicle to move is 20 cents
-a mile. The special rate for charitable
-use of your vehicle to provide relief
-related to Hurricane Katrina has
-expired.
-Elective salary deferrals.
-The
-maximum amount you can defer under
-all plans is generally limited to $15,500
-($10,500 if you only have SIMPLE
-plans; $18,500 for section 403(b) plans
-if you qualify for the 15-year rule). See
-the instructions for line 8 on page 10.
-Mailing your return.
- If you are filing
-the return for an estate or trust, you will
-
-use a different address this year. See
-Where To File on page 4.
-Domestic production activities
-deduction.
-The deduction rate for
-2007 is increased to 6%.
-Unreported social security and
-Medicare tax on wages.
- If you are
-an employee and your employer did not
-withhold social security and Medicare
-tax, see Form 8919 to figure and report
-this tax.
-Refundable credit for prior-year
-minimum tax.
-If you have an unused
-minimum tax credit carryforward from
-2004, see Form 8801 to find if you can
-take this credit.
-Health savings account (HSA)
-funding distributions.
-You may be
-able to elect to exclude from income a
-distribution made from your IRA to your
-HSA. See the instructions for lines 16a
-and 16b beginning on page 12.
-New recordkeeping requirements for
-contributions of money.
- For
-charitable contributions of money,
-regardless of the amount, you must
-maintain as a record of the contribution
-a bank record (such as a cancelled
-check) or a written record from the
-charity. The written record must include
-the name of the charity, date, and
-amount of the contribution. See Gifts to
-U.S. Charities that begins on page 26.
-Exemption for housing a person
-displaced by Hurricane Katrina
-expires.
-The additional exemption
-amount for housing a person displaced
-by Hurricane Katrina does not apply for
-2007 or later years.
-Telephone excise tax credit.
- This
-credit was available only on your 2006
-return. If you filed but did not request it
-on your 2006 return, file Form 1040X
-using a simplified procedure explained
-in its instructions to amend your 2006
-return. If you were not required to file a
-2006 return, see the 2006 Form
-1040EZ-T.
-What’s New for 2008
-IRA deduction expanded.
-You may
-be able to deduct up to $5,000 ($6,000
-if age 50 or older at the end of the
-year). You may be able to take an IRA
-deduction if you were covered by a
-
-Cat. No. 11368V
-
 

samples/nonfree/kampo.txt.ref

@@ -1,12 +1,12 @@
-第 ›Ÿ˜ž 号
+平成 ™— 年 › 月 ™œ 日 金曜日
-
-›
 
 官
 
 報
 
-平成 ™— 年 › 月 ™œ 日 金曜日
+第 ›Ÿ˜ž 号
+
+›
 
 政令第百四十九号
 道路交通法施行令の一部を改正する政令

samples/nonfree/kampo.xml.ref

@@ -1,57 +1,22 @@
 <?xml version="1.0" encoding="utf-8" ?>
 <pages>
 <page id="1" bbox="0.000,0.000,595.000,842.000" rotate="0">
-<textbox id="0" bbox="392.500,787.804,457.500,800.144">
+<textbox id="0" bbox="87.500,787.804,242.500,800.144">
-<textline bbox="392.500,787.804,457.500,800.144">
-<text font="Ryumin-Light" bbox="392.500,787.804,402.500,800.144" size="12.340">第</text>
-<text> </text>
-<text font="GMALPM+DFHSMincho-W3G014" bbox="405.000,789.064,415.000,798.234" size="10.000">›</text>
-<text font="GMALPM+DFHSMincho-W3G014" bbox="415.000,789.064,425.000,798.234" size="10.000">Ÿ</text>
-<text font="GMALPM+DFHSMincho-W3G014" bbox="425.000,789.064,435.000,798.234" size="10.000">˜</text>
-<text font="GMALPM+DFHSMincho-W3G014" bbox="435.000,789.064,445.000,798.234" size="10.000">ž</text>
-<text> </text>
-<text font="Ryumin-Light" bbox="447.500,787.804,457.500,800.144" size="12.340">号</text>
-<text>
-</text>
-</textline>
-</textbox>
-<textbox id="1" bbox="527.500,789.064,537.500,798.234">
-<textline bbox="527.500,789.064,537.500,798.234">
-<text font="GMALPM+DFHSMincho-W3G014" bbox="527.500,789.064,537.500,798.234" size="10.000">›</text>
-<text>
-</text>
-</textline>
-</textbox>
-<textbox id="2" bbox="267.500,787.572,279.500,802.380">
-<textline bbox="267.500,787.572,279.500,802.380">
-<text font="Ryumin-Light" bbox="267.500,787.572,279.500,802.380" size="14.808">官</text>
-<text>
-</text>
-</textline>
-</textbox>
-<textbox id="3" bbox="315.500,787.572,327.500,802.380">
-<textline bbox="315.500,787.572,327.500,802.380">
-<text font="Ryumin-Light" bbox="315.500,787.572,327.500,802.380" size="14.808">報</text>
-<text>
-</text>
-</textline>
-</textbox>
-<textbox id="4" bbox="87.500,787.804,242.500,800.144">
 <textline bbox="87.500,787.804,242.500,800.144">
 <text font="Ryumin-Light" bbox="87.500,787.804,97.500,800.144" size="12.340">平</text>
 <text font="Ryumin-Light" bbox="97.500,787.804,107.500,800.144" size="12.340">成</text>
 <text> </text>
-<text font="GMALPM+DFHSMincho-W3G014" bbox="110.000,789.064,120.000,798.234" size="10.000">™</text>
+<text font="GMALPM+DFHSMincho-W3G014" bbox="110.000,789.064,120.000,798.234" size="9.170">™</text>
-<text font="GMALPM+DFHSMincho-W3G014" bbox="120.000,789.064,130.000,798.234" size="10.000">—</text>
+<text font="GMALPM+DFHSMincho-W3G014" bbox="120.000,789.064,130.000,798.234" size="9.170">—</text>
 <text> </text>
 <text font="Ryumin-Light" bbox="132.500,787.804,142.500,800.144" size="12.340">年</text>
 <text> </text>
-<text font="GMALPM+DFHSMincho-W3G014" bbox="145.000,789.064,155.000,798.234" size="10.000">›</text>
+<text font="GMALPM+DFHSMincho-W3G014" bbox="145.000,789.064,155.000,798.234" size="9.170">›</text>
 <text> </text>
 <text font="Ryumin-Light" bbox="157.500,787.804,167.500,800.144" size="12.340">月</text>
 <text> </text>
-<text font="GMALPM+DFHSMincho-W3G014" bbox="170.000,789.064,180.000,798.234" size="10.000">™</text>
+<text font="GMALPM+DFHSMincho-W3G014" bbox="170.000,789.064,180.000,798.234" size="9.170">™</text>
-<text font="GMALPM+DFHSMincho-W3G014" bbox="180.000,789.064,190.000,798.234" size="10.000">œ</text>
+<text font="GMALPM+DFHSMincho-W3G014" bbox="180.000,789.064,190.000,798.234" size="9.170">œ</text>
 <text> </text>
 <text font="Ryumin-Light" bbox="192.500,787.804,202.500,800.144" size="12.340">日</text>
 <text> </text>
@@ -62,6 +27,41 @@
 </text>
 </textline>
 </textbox>
+<textbox id="1" bbox="267.500,787.572,279.500,802.380">
+<textline bbox="267.500,787.572,279.500,802.380">
+<text font="Ryumin-Light" bbox="267.500,787.572,279.500,802.380" size="14.808">官</text>
+<text>
+</text>
+</textline>
+</textbox>
+<textbox id="2" bbox="315.500,787.572,327.500,802.380">
+<textline bbox="315.500,787.572,327.500,802.380">
+<text font="Ryumin-Light" bbox="315.500,787.572,327.500,802.380" size="14.808">報</text>
+<text>
+</text>
+</textline>
+</textbox>
+<textbox id="3" bbox="392.500,787.804,457.500,800.144">
+<textline bbox="392.500,787.804,457.500,800.144">
+<text font="Ryumin-Light" bbox="392.500,787.804,402.500,800.144" size="12.340">第</text>
+<text> </text>
+<text font="GMALPM+DFHSMincho-W3G014" bbox="405.000,789.064,415.000,798.234" size="9.170">›</text>
+<text font="GMALPM+DFHSMincho-W3G014" bbox="415.000,789.064,425.000,798.234" size="9.170">Ÿ</text>
+<text font="GMALPM+DFHSMincho-W3G014" bbox="425.000,789.064,435.000,798.234" size="9.170">˜</text>
+<text font="GMALPM+DFHSMincho-W3G014" bbox="435.000,789.064,445.000,798.234" size="9.170">ž</text>
+<text> </text>
+<text font="Ryumin-Light" bbox="447.500,787.804,457.500,800.144" size="12.340">号</text>
+<text>
+</text>
+</textline>
+</textbox>
+<textbox id="4" bbox="527.500,789.064,537.500,798.234">
+<textline bbox="527.500,789.064,537.500,798.234">
+<text font="GMALPM+DFHSMincho-W3G014" bbox="527.500,789.064,537.500,798.234" size="9.170">›</text>
+<text>
+</text>
+</textline>
+</textbox>
 <textbox id="5" bbox="420.474,420.036,548.988,781.908" wmode="vertical">
 <textline bbox="540.988,715.796,548.988,781.492">
 <text font="GothicBBB-Medium" bbox="540.988,771.796,548.988,781.492" size="9.696">政</text>
@@ -3136,16 +3136,16 @@
 <layout>
 <textgroup bbox="45.212,52.036,549.776,802.380">
 <textgroup bbox="87.500,787.572,537.500,802.380">
-<textgroup bbox="392.500,787.804,537.500,800.144">
-<textbox id="0" bbox="392.500,787.804,457.500,800.144" />
-<textbox id="1" bbox="527.500,789.064,537.500,798.234" />
-</textgroup>
 <textgroup bbox="87.500,787.572,327.500,802.380">
+<textbox id="0" bbox="87.500,787.804,242.500,800.144" />
 <textgroup bbox="267.500,787.572,327.500,802.380">
-<textbox id="2" bbox="267.500,787.572,279.500,802.380" />
+<textbox id="1" bbox="267.500,787.572,279.500,802.380" />
-<textbox id="3" bbox="315.500,787.572,327.500,802.380" />
+<textbox id="2" bbox="315.500,787.572,327.500,802.380" />
 </textgroup>
-<textbox id="4" bbox="87.500,787.804,242.500,800.144" />
+</textgroup>
+<textgroup bbox="392.500,787.804,537.500,800.144">
+<textbox id="3" bbox="392.500,787.804,457.500,800.144" />
+<textbox id="4" bbox="527.500,789.064,537.500,798.234" />
 </textgroup>
 </textgroup>
 <textgroup bbox="45.212,52.036,549.776,781.960">

samples/nonfree/naacl06-shinyama.txt.ref

@@ -28,46 +28,37 @@ good results.
 1 Background
 
 Every day, a large number of news articles are cre-
-ated and reported, many of which are unique.
+ated and reported, many of which are unique. But
-But
 certain types of events, such as hurricanes or mur-
 ders, are reported again and again throughout a year.
 The goal of Information Extraction, or IE, is to re-
 trieve a certain type of news event from past articles
 and present the events as a table whose columns are
 filled with a name of a person or company, accord-
-However, existing IE
+ing to its role in the event. However, existing IE
-ing to its role in the event.
+techniques require a lot of human labor. First, you
-techniques require a lot of human labor.
-First, you
 have to specify the type of information you want and
-collect articles that include this information.
+collect articles that include this information. Then,
-Then,
 you have to analyze the articles and manually craft
 a set of patterns to capture these events. Most exist-
 ing IE research focuses on reducing this burden by
-helping people create such patterns.
+helping people create such patterns. But each time
-But each time
 you want to extract a different kind of information,
 you need to repeat the whole process: specify arti-
 
 cles and adjust its patterns, either manually or semi-
-automatically.
+automatically. There is a bit of a dangerous pitfall
-There is a bit of a dangerous pitfall
 here. First, it is hard to estimate how good the sys-
 tem can be after months of work. Furthermore, you
 might not know if the task is even doable in the first
-place.
+place. Knowing what kind of information is easily
-Knowing what kind of information is easily
 obtained in advance would help reduce this risk.
 An IE task can be defined as finding a relation
 among several entities involved in a certain type of
-event.
+event. For example, in the MUC-6 management
-For example, in the MUC-6 management
 succession scenario, one seeks a relation between
 COMPANY, PERSON and POST involved with hir-
-ing/firing events.
+ing/firing events. For each row of an extracted ta-
-For each row of an extracted ta-
 ble, you can always read it as “COMPANY hired
 (or fired) PERSON for POST.” The relation between
 these entities is retained throughout the table. There

samples/nonfree/naacl06-shinyama.xml.ref

@@ -871,7 +871,7 @@
 <text>
 </text>
 </textline>
-<textline bbox="72.000,336.427,276.805,349.577">
+<textline bbox="72.000,336.427,298.882,349.577">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="72.000,336.427,76.845,349.577" size="13.150">a</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="76.845,336.427,79.879,349.577" size="13.150">t</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="79.879,336.427,84.725,349.577" size="13.150">e</text>
@@ -916,10 +916,7 @@
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="263.775,336.427,269.232,349.577" size="13.150">u</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="269.232,336.427,274.077,349.577" size="13.150">e</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="274.077,336.427,276.805,349.577" size="13.150">.</text>
-<text>
+<text> </text>
-</text>
-</textline>
-<textline bbox="283.113,336.427,298.882,349.577">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="283.113,336.427,290.392,349.577" size="13.150">B</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="290.392,336.427,295.849,349.577" size="13.150">u</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="295.849,336.427,298.882,349.577" size="13.150">t</text>
@@ -1260,31 +1257,7 @@
 <text>
 </text>
 </textline>
-<textline bbox="203.557,241.580,298.882,254.730">
+<textline bbox="72.000,241.580,298.882,254.730">
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="203.557,241.580,211.436,254.730" size="13.150">H</text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="211.436,241.580,216.893,254.730" size="13.150">o</text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="216.631,241.580,224.510,254.730" size="13.150">w</text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="224.510,241.580,229.355,254.730" size="13.150">e</text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="229.083,241.580,234.539,254.730" size="13.150">v</text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="234.375,241.580,239.221,254.730" size="13.150">e</text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="239.221,241.580,242.855,254.730" size="13.150">r</text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="242.418,241.580,245.147,254.730" size="13.150">,</text>
-<text> </text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="249.861,241.580,254.706,254.730" size="13.150">e</text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="254.554,241.580,260.010,254.730" size="13.150">x</text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="260.010,241.580,263.044,254.730" size="13.150">i</text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="263.044,241.580,267.289,254.730" size="13.150">s</text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="267.289,241.580,270.323,254.730" size="13.150">t</text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="270.323,241.580,273.357,254.730" size="13.150">i</text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="273.357,241.580,278.813,254.730" size="13.150">n</text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="278.813,241.580,284.270,254.730" size="13.150">g</text>
-<text> </text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="288.580,241.580,292.215,254.730" size="13.150">I</text>
-<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="292.215,241.580,298.882,254.730" size="13.150">E</text>
-<text>
-</text>
-</textline>
-<textline bbox="72.000,241.580,195.405,254.730">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="72.000,241.580,75.034,254.730" size="13.150">i</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="75.034,241.580,80.490,254.730" size="13.150">n</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="80.490,241.580,85.947,254.730" size="13.150">g</text>
@@ -1314,10 +1287,31 @@
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="184.186,241.580,189.643,254.730" size="13.150">n</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="189.643,241.580,192.677,254.730" size="13.150">t</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="192.677,241.580,195.405,254.730" size="13.150">.</text>
+<text> </text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="203.557,241.580,211.436,254.730" size="13.150">H</text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="211.436,241.580,216.893,254.730" size="13.150">o</text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="216.631,241.580,224.510,254.730" size="13.150">w</text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="224.510,241.580,229.355,254.730" size="13.150">e</text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="229.083,241.580,234.539,254.730" size="13.150">v</text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="234.375,241.580,239.221,254.730" size="13.150">e</text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="239.221,241.580,242.855,254.730" size="13.150">r</text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="242.418,241.580,245.147,254.730" size="13.150">,</text>
+<text> </text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="249.861,241.580,254.706,254.730" size="13.150">e</text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="254.554,241.580,260.010,254.730" size="13.150">x</text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="260.010,241.580,263.044,254.730" size="13.150">i</text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="263.044,241.580,267.289,254.730" size="13.150">s</text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="267.289,241.580,270.323,254.730" size="13.150">t</text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="270.323,241.580,273.357,254.730" size="13.150">i</text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="273.357,241.580,278.813,254.730" size="13.150">n</text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="278.813,241.580,284.270,254.730" size="13.150">g</text>
+<text> </text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="288.580,241.580,292.215,254.730" size="13.150">I</text>
+<text font="QTLIUY+NimbusRomNo9L-Regu" bbox="292.215,241.580,298.882,254.730" size="13.150">E</text>
 <text>
 </text>
 </textline>
-<textline bbox="72.000,228.026,250.352,241.177">
+<textline bbox="72.000,228.026,298.882,241.177">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="72.000,228.026,75.034,241.177" size="13.150">t</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="75.034,228.026,79.879,241.177" size="13.150">e</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="79.879,228.026,84.725,241.177" size="13.150">c</text>
@@ -1358,10 +1352,7 @@
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="239.123,228.026,244.579,241.177" size="13.150">o</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="244.579,228.026,248.213,241.177" size="13.150">r</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="247.624,228.026,250.352,241.177" size="13.150">.</text>
-<text>
+<text> </text>
-</text>
-</textline>
-<textline bbox="256.060,228.026,298.882,241.177">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="256.060,228.026,262.127,241.177" size="13.150">F</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="262.127,228.026,265.161,241.177" size="13.150">i</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="265.161,228.026,268.795,241.177" size="13.150">r</text>
@@ -1431,7 +1422,7 @@
 <text>
 </text>
 </textline>
-<textline bbox="72.000,200.929,268.249,214.079">
+<textline bbox="72.000,200.929,298.882,214.079">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="72.000,200.929,76.845,214.079" size="13.150">c</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="76.845,200.929,82.302,214.079" size="13.150">o</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="82.302,200.929,85.336,214.079" size="13.150">l</text>
@@ -1479,10 +1470,7 @@
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="254.608,200.929,260.065,214.079" size="13.150">o</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="260.065,200.929,265.521,214.079" size="13.150">n</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="265.521,200.929,268.249,214.079" size="13.150">.</text>
-<text>
+<text> </text>
-</text>
-</textline>
-<textline bbox="273.728,200.929,298.882,214.079">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="273.728,200.929,280.396,214.079" size="13.150">T</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="280.396,200.929,285.852,214.079" size="13.150">h</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="285.852,200.929,290.698,214.079" size="13.150">e</text>
@@ -1658,7 +1646,7 @@
 <text>
 </text>
 </textline>
-<textline bbox="72.000,146.734,231.091,159.884">
+<textline bbox="72.000,146.734,298.882,159.884">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="72.000,146.734,77.457,159.884" size="13.150">h</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="77.457,146.734,82.302,159.884" size="13.150">e</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="82.302,146.734,85.336,159.884" size="13.150">l</text>
@@ -1695,10 +1683,7 @@
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="218.661,146.734,224.117,159.884" size="13.150">n</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="224.117,146.734,228.362,159.884" size="13.150">s</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="228.362,146.734,231.091,159.884" size="13.150">.</text>
-<text>
+<text> </text>
-</text>
-</textline>
-<textline bbox="236.743,146.734,298.882,159.884">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="236.743,146.734,244.022,159.884" size="13.150">B</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="244.022,146.734,249.479,159.884" size="13.150">u</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="249.479,146.734,252.513,159.884" size="13.150">t</text>
@@ -1886,7 +1871,7 @@
 <text>
 </text>
 </textline>
-<textline bbox="313.198,581.125,374.638,594.275">
+<textline bbox="313.198,581.125,540.091,594.275">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="313.198,581.125,318.043,594.275" size="13.150">a</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="318.043,581.125,323.499,594.275" size="13.150">u</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="323.499,581.125,326.533,594.275" size="13.150">t</text>
@@ -1901,10 +1886,7 @@
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="364.118,581.125,367.152,594.275" size="13.150">l</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="367.152,581.125,372.608,594.275" size="13.150">y</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="371.910,581.125,374.638,594.275" size="13.150">.</text>
-<text>
+<text> </text>
-</text>
-</textline>
-<textline bbox="380.749,581.125,540.091,594.275">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="380.749,581.125,387.417,594.275" size="13.150">T</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="387.417,581.125,392.874,594.275" size="13.150">h</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="392.874,581.125,397.719,594.275" size="13.150">e</text>
@@ -2112,17 +2094,14 @@
 <text>
 </text>
 </textline>
-<textline bbox="313.198,526.930,338.952,540.080">
+<textline bbox="313.198,526.930,540.080,540.080">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="313.198,526.930,318.654,540.080" size="13.150">p</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="318.654,526.930,321.688,540.080" size="13.150">l</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="321.688,526.930,326.533,540.080" size="13.150">a</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="326.533,526.930,331.379,540.080" size="13.150">c</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="331.379,526.930,336.224,540.080" size="13.150">e</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="336.224,526.930,338.952,540.080" size="13.150">.</text>
-<text>
+<text> </text>
-</text>
-</textline>
-<textline bbox="344.682,526.930,540.080,540.080">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="344.682,526.930,352.561,540.080" size="13.150">K</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="352.561,526.930,358.017,540.080" size="13.150">n</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="358.017,526.930,363.474,540.080" size="13.150">o</text>
@@ -2325,17 +2304,14 @@
 <text>
 </text>
 </textline>
-<textline bbox="313.198,472.325,339.138,485.475">
+<textline bbox="313.198,472.325,540.080,485.475">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="313.198,472.325,318.043,485.475" size="13.150">e</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="317.781,472.325,323.238,485.475" size="13.150">v</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="323.074,472.325,327.919,485.475" size="13.150">e</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="327.919,472.325,333.376,485.475" size="13.150">n</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="333.376,472.325,336.410,485.475" size="13.150">t</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="336.410,472.325,339.138,485.475" size="13.150">.</text>
-<text>
+<text> </text>
-</text>
-</textline>
-<textline bbox="349.003,472.325,540.080,485.475">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="349.003,472.325,355.071,485.475" size="13.150">F</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="354.918,472.325,360.375,485.475" size="13.150">o</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="360.375,472.325,364.009,485.475" size="13.150">r</text>
@@ -2475,7 +2451,7 @@
 <text>
 </text>
 </textline>
-<textline bbox="313.198,431.673,387.854,444.824">
+<textline bbox="313.198,431.673,540.080,444.824">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="313.198,431.673,316.231,444.824" size="13.150">i</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="316.231,431.673,321.688,444.824" size="13.150">n</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="321.688,431.673,327.144,444.824" size="13.150">g</text>
@@ -2493,10 +2469,7 @@
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="377.846,431.673,380.880,444.824" size="13.150">t</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="380.880,431.673,385.125,444.824" size="13.150">s</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="385.125,431.673,387.854,444.824" size="13.150">.</text>
-<text>
+<text> </text>
-</text>
-</textline>
-<textline bbox="394.576,431.673,540.080,444.824">
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="394.576,431.673,400.644,444.824" size="13.150">F</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="400.491,431.673,405.948,444.824" size="13.150">o</text>
 <text font="QTLIUY+NimbusRomNo9L-Regu" bbox="405.948,431.673,409.582,444.824" size="13.150">r</text>

samples/nonfree/nlp2004slides.html.ref

@@ -3,92 +3,13 @@
 </head><body>
 <span style="position:absolute; border: gray 1px solid; left:0px; top:50px; width:800px; height:600px;"></span>
 <div style="position:absolute; top:50px;"><a name="1">Page 1</a></div>
-<span style="position:absolute; border: cyan 1px solid; left:62px; top:126px; width:672px; height:157px;"></span>
+<div style="position:absolute; border: textbox 1px solid; writing-mode:lr-tb; left:62px; top:126px; width:672px; height:157px;"><span style="font-family: DAFPJF+HiraKakuPro-W6; font-size:60px">コンパラブルな新聞記事からの
-<span style="position:absolute; border: magenta 1px solid; left:62px; top:126px; width:672px; height:85px;"></span>
+<br>固有表現の発見
-<span style="position:absolute; left:62px; top:126px; font-size:85px;">コ</span>
+<br></span></div><div style="position:absolute; border: textbox 1px solid; writing-mode:lr-tb; left:263px; top:374px; width:468px; height:212px;"><span style="font-family: DAFPJF+HiraKakuPro-W6; font-size:45px">新山 祐介
-<span style="position:absolute; left:110px; top:126px; font-size:85px;">ン</span>
+<br>関根 聡
-<span style="position:absolute; left:158px; top:126px; font-size:85px;">パ</span>
+<br></span><span style="font-family: DAFPJF+HiraKakuPro-W6; font-size:35px">Computer Science Department
-<span style="position:absolute; left:206px; top:126px; font-size:85px;">ラ</span>
+<br>New York University
-<span style="position:absolute; left:254px; top:126px; font-size:85px;">ブ</span>
+<br></span></div><span style="position:absolute; border: black 1px solid; left:0px; top:50px; width:800px; height:600px;"></span>
-<span style="position:absolute; left:302px; top:126px; font-size:85px;">ル</span>
-<span style="position:absolute; left:350px; top:126px; font-size:85px;">な</span>
-<span style="position:absolute; left:398px; top:126px; font-size:85px;">新</span>
-<span style="position:absolute; left:446px; top:126px; font-size:85px;">聞</span>
-<span style="position:absolute; left:494px; top:126px; font-size:85px;">記</span>
-<span style="position:absolute; left:542px; top:126px; font-size:85px;">事</span>
-<span style="position:absolute; left:590px; top:126px; font-size:85px;">か</span>
-<span style="position:absolute; left:638px; top:126px; font-size:85px;">ら</span>
-<span style="position:absolute; left:686px; top:126px; font-size:85px;">の</span>
-<span style="position:absolute; border: magenta 1px solid; left:62px; top:198px; width:336px; height:85px;"></span>
-<span style="position:absolute; left:62px; top:198px; font-size:85px;">固</span>
-<span style="position:absolute; left:110px; top:198px; font-size:85px;">有</span>
-<span style="position:absolute; left:158px; top:198px; font-size:85px;">表</span>
-<span style="position:absolute; left:206px; top:198px; font-size:85px;">現</span>
-<span style="position:absolute; left:254px; top:198px; font-size:85px;">の</span>
-<span style="position:absolute; left:302px; top:198px; font-size:85px;">発</span>
-<span style="position:absolute; left:350px; top:198px; font-size:85px;">見</span>
-<span style="position:absolute; border: cyan 1px solid; left:263px; top:374px; width:468px; height:212px;"></span>
-<span style="position:absolute; border: magenta 1px solid; left:576px; top:374px; width:155px; height:64px;"></span>
-<span style="position:absolute; left:576px; top:374px; font-size:64px;">新</span>
-<span style="position:absolute; left:612px; top:374px; font-size:64px;">山</span>
-<span style="position:absolute; left:648px; top:374px; font-size:64px;"> </span>
-<span style="position:absolute; left:660px; top:374px; font-size:64px;">祐</span>
-<span style="position:absolute; left:696px; top:374px; font-size:64px;">介</span>
-<span style="position:absolute; border: magenta 1px solid; left:612px; top:430px; width:119px; height:64px;"></span>
-<span style="position:absolute; left:612px; top:430px; font-size:64px;">関</span>
-<span style="position:absolute; left:648px; top:430px; font-size:64px;">根</span>
-<span style="position:absolute; left:684px; top:430px; font-size:64px;"> </span>
-<span style="position:absolute; left:696px; top:430px; font-size:64px;">聡</span>
-<span style="position:absolute; border: magenta 1px solid; left:263px; top:493px; width:468px; height:50px;"></span>
-<span style="position:absolute; left:263px; top:493px; font-size:50px;">C</span>
-<span style="position:absolute; left:285px; top:493px; font-size:50px;">o</span>
-<span style="position:absolute; left:304px; top:493px; font-size:50px;">m</span>
-<span style="position:absolute; left:332px; top:493px; font-size:50px;">p</span>
-<span style="position:absolute; left:352px; top:493px; font-size:50px;">u</span>
-<span style="position:absolute; left:371px; top:493px; font-size:50px;">t</span>
-<span style="position:absolute; left:383px; top:493px; font-size:50px;">e</span>
-<span style="position:absolute; left:401px; top:493px; font-size:50px;">r</span>
-<span style="position:absolute; left:415px; top:493px; font-size:50px;"> </span>
-<span style="position:absolute; left:424px; top:493px; font-size:50px;">S</span>
-<span style="position:absolute; left:444px; top:493px; font-size:50px;">c</span>
-<span style="position:absolute; left:462px; top:493px; font-size:50px;">i</span>
-<span style="position:absolute; left:469px; top:493px; font-size:50px;">e</span>
-<span style="position:absolute; left:487px; top:493px; font-size:50px;">n</span>
-<span style="position:absolute; left:506px; top:493px; font-size:50px;">c</span>
-<span style="position:absolute; left:523px; top:493px; font-size:50px;">e</span>
-<span style="position:absolute; left:541px; top:493px; font-size:50px;"> </span>
-<span style="position:absolute; left:550px; top:493px; font-size:50px;">D</span>
-<span style="position:absolute; left:573px; top:493px; font-size:50px;">e</span>
-<span style="position:absolute; left:591px; top:493px; font-size:50px;">p</span>
-<span style="position:absolute; left:611px; top:493px; font-size:50px;">a</span>
-<span style="position:absolute; left:628px; top:493px; font-size:50px;">r</span>
-<span style="position:absolute; left:642px; top:493px; font-size:50px;">t</span>
-<span style="position:absolute; left:654px; top:493px; font-size:50px;">m</span>
-<span style="position:absolute; left:683px; top:493px; font-size:50px;">e</span>
-<span style="position:absolute; left:701px; top:493px; font-size:50px;">n</span>
-<span style="position:absolute; left:719px; top:493px; font-size:50px;">t</span>
-<span style="position:absolute; border: magenta 1px solid; left:424px; top:537px; width:307px; height:50px;"></span>
-<span style="position:absolute; left:424px; top:537px; font-size:50px;">N</span>
-<span style="position:absolute; left:447px; top:537px; font-size:50px;">e</span>
-<span style="position:absolute; left:464px; top:537px; font-size:50px;">w</span>
-<span style="position:absolute; left:488px; top:537px; font-size:50px;"> </span>
-<span style="position:absolute; left:498px; top:537px; font-size:50px;">Y</span>
-<span style="position:absolute; left:519px; top:537px; font-size:50px;">o</span>
-<span style="position:absolute; left:538px; top:537px; font-size:50px;">r</span>
-<span style="position:absolute; left:551px; top:537px; font-size:50px;">k</span>
-<span style="position:absolute; left:570px; top:537px; font-size:50px;"> </span>
-<span style="position:absolute; left:579px; top:537px; font-size:50px;">U</span>
-<span style="position:absolute; left:602px; top:537px; font-size:50px;">n</span>
-<span style="position:absolute; left:621px; top:537px; font-size:50px;">i</span>
-<span style="position:absolute; left:629px; top:537px; font-size:50px;">v</span>
-<span style="position:absolute; left:646px; top:537px; font-size:50px;">e</span>
-<span style="position:absolute; left:664px; top:537px; font-size:50px;">r</span>
-<span style="position:absolute; left:678px; top:537px; font-size:50px;">s</span>
-<span style="position:absolute; left:694px; top:537px; font-size:50px;">i</span>
-<span style="position:absolute; left:702px; top:537px; font-size:50px;">t</span>
-<span style="position:absolute; left:714px; top:537px; font-size:50px;">y</span>
-<span style="position:absolute; border: black 1px solid; left:0px; top:50px; width:800px; height:600px;"></span>
 <span style="position:absolute; border: black 1px solid; left:50px; top:308px; width:510px; height:0px;"></span>
-<span style="position:absolute; border: yellow 1px solid; left:25px; top:587px; width:41px; height:40px;"></span>
 <div style="position:absolute; top:0px;">Page: <a href="#1">1</a></div>
 </body></html>

samples/simple1.html.ref

@@ -3,65 +3,13 @@
 </head><body>
 <span style="position:absolute; border: gray 1px solid; left:0px; top:50px; width:612px; height:792px;"></span>
 <div style="position:absolute; top:50px;"><a name="1">Page 1</a></div>
-<span style="position:absolute; border: cyan 1px solid; left:100px; top:119px; width:61px; height:27px;"></span>
+<div style="position:absolute; border: textbox 1px solid; writing-mode:lr-tb; left:100px; top:119px; width:61px; height:27px;"><span style="font-family: Helvetica; font-size:19px">Hello 
-<span style="position:absolute; border: magenta 1px solid; left:100px; top:119px; width:61px; height:27px;"></span>
+<br></span></div><div style="position:absolute; border: textbox 1px solid; writing-mode:lr-tb; left:261px; top:119px; width:62px; height:27px;"><span style="font-family: Helvetica; font-size:19px">World
-<span style="position:absolute; left:100px; top:119px; font-size:27px;">H</span>
+<br></span></div><div style="position:absolute; border: textbox 1px solid; writing-mode:lr-tb; left:100px; top:219px; width:61px; height:27px;"><span style="font-family: Helvetica; font-size:19px">Hello 
-<span style="position:absolute; left:117px; top:119px; font-size:27px;">e</span>
+<br></span></div><div style="position:absolute; border: textbox 1px solid; writing-mode:lr-tb; left:261px; top:219px; width:62px; height:27px;"><span style="font-family: Helvetica; font-size:19px">World
-<span style="position:absolute; left:130px; top:119px; font-size:27px;">l</span>
+<br></span></div><div style="position:absolute; border: textbox 1px solid; writing-mode:lr-tb; left:100px; top:319px; width:111px; height:27px;"><span style="font-family: Helvetica; font-size:19px">H e l l o  
-<span style="position:absolute; left:136px; top:119px; font-size:27px;">l</span>
+<br></span></div><div style="position:absolute; border: textbox 1px solid; writing-mode:lr-tb; left:321px; top:319px; width:102px; height:27px;"><span style="font-family: Helvetica; font-size:19px">W o r l d
-<span style="position:absolute; left:141px; top:119px; font-size:27px;">o</span>
+<br></span></div><div style="position:absolute; border: textbox 1px solid; writing-mode:lr-tb; left:100px; top:419px; width:111px; height:27px;"><span style="font-family: Helvetica; font-size:19px">H e l l o  
-<span style="position:absolute; left:154px; top:119px; font-size:27px;"> </span>
+<br></span></div><div style="position:absolute; border: textbox 1px solid; writing-mode:lr-tb; left:321px; top:419px; width:102px; height:27px;"><span style="font-family: Helvetica; font-size:19px">W o r l d
-<span style="position:absolute; border: cyan 1px solid; left:261px; top:119px; width:62px; height:27px;"></span>
+<br></span></div><div style="position:absolute; top:0px;">Page: <a href="#1">1</a></div>
-<span style="position:absolute; border: magenta 1px solid; left:261px; top:119px; width:62px; height:27px;"></span>
-<span style="position:absolute; left:261px; top:119px; font-size:27px;">W</span>
-<span style="position:absolute; left:283px; top:119px; font-size:27px;">o</span>
-<span style="position:absolute; left:297px; top:119px; font-size:27px;">r</span>
-<span style="position:absolute; left:305px; top:119px; font-size:27px;">l</span>
-<span style="position:absolute; left:310px; top:119px; font-size:27px;">d</span>
-<span style="position:absolute; border: cyan 1px solid; left:100px; top:219px; width:61px; height:27px;"></span>
-<span style="position:absolute; border: magenta 1px solid; left:100px; top:219px; width:61px; height:27px;"></span>
-<span style="position:absolute; left:100px; top:219px; font-size:27px;">H</span>
-<span style="position:absolute; left:117px; top:219px; font-size:27px;">e</span>
-<span style="position:absolute; left:130px; top:219px; font-size:27px;">l</span>
-<span style="position:absolute; left:136px; top:219px; font-size:27px;">l</span>
-<span style="position:absolute; left:141px; top:219px; font-size:27px;">o</span>
-<span style="position:absolute; left:154px; top:219px; font-size:27px;"> </span>
-<span style="position:absolute; border: cyan 1px solid; left:261px; top:219px; width:62px; height:27px;"></span>
-<span style="position:absolute; border: magenta 1px solid; left:261px; top:219px; width:62px; height:27px;"></span>
-<span style="position:absolute; left:261px; top:219px; font-size:27px;">W</span>
-<span style="position:absolute; left:284px; top:219px; font-size:27px;">o</span>
-<span style="position:absolute; left:297px; top:219px; font-size:27px;">r</span>
-<span style="position:absolute; left:305px; top:219px; font-size:27px;">l</span>
-<span style="position:absolute; left:310px; top:219px; font-size:27px;">d</span>
-<span style="position:absolute; border: cyan 1px solid; left:100px; top:319px; width:111px; height:27px;"></span>
-<span style="position:absolute; border: magenta 1px solid; left:100px; top:319px; width:111px; height:27px;"></span>
-<span style="position:absolute; left:100px; top:319px; font-size:27px;">H</span>
-<span style="position:absolute; left:127px; top:319px; font-size:27px;">e</span>
-<span style="position:absolute; left:150px; top:319px; font-size:27px;">l</span>
-<span style="position:absolute; left:166px; top:319px; font-size:27px;">l</span>
-<span style="position:absolute; left:181px; top:319px; font-size:27px;">o</span>
-<span style="position:absolute; left:204px; top:319px; font-size:27px;"> </span>
-<span style="position:absolute; border: cyan 1px solid; left:321px; top:319px; width:102px; height:27px;"></span>
-<span style="position:absolute; border: magenta 1px solid; left:321px; top:319px; width:102px; height:27px;"></span>
-<span style="position:absolute; left:321px; top:319px; font-size:27px;">W</span>
-<span style="position:absolute; left:354px; top:319px; font-size:27px;">o</span>
-<span style="position:absolute; left:377px; top:319px; font-size:27px;">r</span>
-<span style="position:absolute; left:395px; top:319px; font-size:27px;">l</span>
-<span style="position:absolute; left:410px; top:319px; font-size:27px;">d</span>
-<span style="position:absolute; border: cyan 1px solid; left:100px; top:419px; width:111px; height:27px;"></span>
-<span style="position:absolute; border: magenta 1px solid; left:100px; top:419px; width:111px; height:27px;"></span>
-<span style="position:absolute; left:100px; top:419px; font-size:27px;">H</span>
-<span style="position:absolute; left:127px; top:419px; font-size:27px;">e</span>
-<span style="position:absolute; left:150px; top:419px; font-size:27px;">l</span>
-<span style="position:absolute; left:165px; top:419px; font-size:27px;">l</span>
-<span style="position:absolute; left:181px; top:419px; font-size:27px;">o</span>
-<span style="position:absolute; left:204px; top:419px; font-size:27px;"> </span>
-<span style="position:absolute; border: cyan 1px solid; left:321px; top:419px; width:102px; height:27px;"></span>
-<span style="position:absolute; border: magenta 1px solid; left:321px; top:419px; width:102px; height:27px;"></span>
-<span style="position:absolute; left:321px; top:419px; font-size:27px;">W</span>
-<span style="position:absolute; left:353px; top:419px; font-size:27px;">o</span>
-<span style="position:absolute; left:377px; top:419px; font-size:27px;">r</span>
-<span style="position:absolute; left:395px; top:419px; font-size:27px;">l</span>
-<span style="position:absolute; left:410px; top:419px; font-size:27px;">d</span>
-<div style="position:absolute; top:0px;">Page: <a href="#1">1</a></div>
 </body></html>

samples/simple3.html.ref

@@ -3,42 +3,9 @@
 </head><body>
 <span style="position:absolute; border: gray 1px solid; left:0px; top:50px; width:612px; height:792px;"></span>
 <div style="position:absolute; top:50px;"><a name="1">Page 1</a></div>
-<span style="position:absolute; border: cyan 1px solid; left:0px; top:72px; width:218px; height:79px;"></span>
+<div style="position:absolute; border: textbox 1px solid; writing-mode:lr-tb; left:0px; top:72px; width:218px; height:79px;"><span style="font-family: Helvetica; font-size:38px">HelloHello
-<span style="position:absolute; border: magenta 1px solid; left:0px; top:72px; width:218px; height:79px;"></span>
+<br></span></div><div style="position:absolute; border: textbox 1px solid; writing-mode:tb-rl; left:194px; top:136px; width:48px; height:490px;"><span style="font-family: unknown; font-size:33px">あいうえおあいうえお </span><span style="font-family: Helvetica; font-size:19px">W
-<span style="position:absolute; left:0px; top:96px; font-size:55px;">H</span>
+<br></span></div><div style="position:absolute; border: textbox 1px solid; writing-mode:lr-tb; left:241px; top:575px; width:102px; height:51px;"><span style="font-family: Helvetica; font-size:19px">World
-<span style="position:absolute; left:34px; top:96px; font-size:55px;">e</span>
+<br>orld
-<span style="position:absolute; left:61px; top:96px; font-size:55px;">l</span>
+<br></span></div><div style="position:absolute; top:0px;">Page: <a href="#1">1</a></div>
-<span style="position:absolute; left:72px; top:96px; font-size:55px;">l</span>
-<span style="position:absolute; left:82px; top:96px; font-size:55px;">o</span>
-<span style="position:absolute; left:109px; top:72px; font-size:55px;">H</span>
-<span style="position:absolute; left:144px; top:72px; font-size:55px;">e</span>
-<span style="position:absolute; left:170px; top:72px; font-size:55px;">l</span>
-<span style="position:absolute; left:181px; top:72px; font-size:55px;">l</span>
-<span style="position:absolute; left:192px; top:72px; font-size:55px;">o</span>
-<span style="position:absolute; border: cyan 1px solid; left:194px; top:136px; width:48px; height:490px;"></span>
-<span style="position:absolute; border: magenta 1px solid; left:194px; top:136px; width:48px; height:490px;"></span>
-<span style="position:absolute; left:194px; top:136px; font-size:48px;">あ</span>
-<span style="position:absolute; left:194px; top:184px; font-size:48px;">い</span>
-<span style="position:absolute; left:194px; top:232px; font-size:48px;">う</span>
-<span style="position:absolute; left:194px; top:280px; font-size:48px;">え</span>
-<span style="position:absolute; left:194px; top:328px; font-size:48px;">お</span>
-<span style="position:absolute; left:194px; top:352px; font-size:48px;">あ</span>
-<span style="position:absolute; left:194px; top:400px; font-size:48px;">い</span>
-<span style="position:absolute; left:194px; top:448px; font-size:48px;">う</span>
-<span style="position:absolute; left:194px; top:496px; font-size:48px;">え</span>
-<span style="position:absolute; left:194px; top:544px; font-size:48px;">お</span>
-<span style="position:absolute; left:218px; top:599px; font-size:27px;">W</span>
-<span style="position:absolute; border: cyan 1px solid; left:241px; top:575px; width:102px; height:51px;"></span>
-<span style="position:absolute; border: magenta 1px solid; left:281px; top:575px; width:62px; height:27px;"></span>
-<span style="position:absolute; left:281px; top:575px; font-size:27px;">W</span>
-<span style="position:absolute; left:304px; top:575px; font-size:27px;">o</span>
-<span style="position:absolute; left:317px; top:575px; font-size:27px;">r</span>
-<span style="position:absolute; left:325px; top:575px; font-size:27px;">l</span>
-<span style="position:absolute; left:330px; top:575px; font-size:27px;">d</span>
-<span style="position:absolute; border: magenta 1px solid; left:241px; top:599px; width:40px; height:27px;"></span>
-<span style="position:absolute; left:241px; top:599px; font-size:27px;">o</span>
-<span style="position:absolute; left:254px; top:599px; font-size:27px;">r</span>
-<span style="position:absolute; left:262px; top:599px; font-size:27px;">l</span>
-<span style="position:absolute; left:268px; top:599px; font-size:27px;">d</span>
-<div style="position:absolute; top:0px;">Page: <a href="#1">1</a></div>
 </body></html>

tools/pdf2html.cgi

@@ -1,4 +1,4 @@
-#!/usr/bin/python2 -O
+#!/usr/bin/python -O
 #
 # pdf2html.cgi - Gateway script for converting PDF into HTML.
 #
@@ -42,7 +42,7 @@ def url(base, **kw):
 ##  convert
 ##
 class FileSizeExceeded(ValueError): pass
-def convert(outfp, infp, path, codec='utf-8',
+def convert(infp, outfp, path, codec='utf-8',
             maxpages=0, maxfilesize=0, pagenos=None,
             html=True):
     # save the input file.
@@ -76,22 +76,22 @@ def convert(outfp, infp, path, codec='utf-8',
 class WebApp(object):
 
     TITLE = 'pdf2html demo'
-    APPPATH = '/'        # absolute URL path to this application. 
+    MAXFILESIZE = 10000000             # set to zero if unlimited.
-    MAXFILESIZE = 5000000              # set to zero if unlimited.
     MAXPAGES = 10                      # set to zero if unlimited.
 
-    def __init__(self, infp=sys.stdin, outfp=sys.stdout, codec='utf-8'):
+    def __init__(self, infp=sys.stdin, outfp=sys.stdout, environ=os.environ,
+                 codec='utf-8', apppath='/'):
+        self.infp = infp
         self.outfp = outfp
         self.codec = codec
-        self.remote_addr = os.environ.get('REMOTE_ADDR')
+        self.apppath = apppath
-        self.path_info = os.environ.get('PATH_INFO')
+        self.remote_addr = environ.get('REMOTE_ADDR')
-        self.method = os.environ.get('REQUEST_METHOD', 'GET').upper()
+        self.path_info = environ.get('PATH_INFO')
-        self.server = os.environ.get('SERVER_SOFTWARE', '')
+        self.method = environ.get('REQUEST_METHOD', 'GET').upper()
-        self.logpath = os.environ.get('LOG_PATH', './var/log')
+        self.server = environ.get('SERVER_SOFTWARE', '')
-        self.tmpdir = os.environ.get('TEMP', './var/')
+        self.tmpdir = environ.get('TEMP', './var/')
         self.content_type = 'text/html; charset=%s' % codec
-        self.cur_time = time.time()
+        self.logger = logging.getLogger()
-        self.form = cgi.FieldStorage(infp)
         return
 
     def put(self, *args):
@@ -130,7 +130,7 @@ class WebApp(object):
         self.put(
           '<html><head><title>%s</title></head><body>\n' % q(self.TITLE),
           '<h1>%s</h1><hr>\n' % q(self.TITLE),
-          '<form method="POST" action="%s" enctype="multipart/form-data">\n' % q(self.APPPATH),
+          '<form method="POST" action="%s" enctype="multipart/form-data">\n' % q(self.apppath),
           '<p>Upload PDF File: <input name="f" type="file" value="">\n',
           '&nbsp; Page numbers (comma-separated):\n',
           '<input name="p" type="text" size="10" value="">\n',
@@ -145,49 +145,54 @@ class WebApp(object):
           )
         return
 
-    def run(self, argv):
+    def setup(self):
-        logging.basicConfig(level=logging.INFO,
+        if not os.path.isdir(self.tmpdir):
-                            format='%(asctime)s %(levelname)s %(message)s',
+            self.logger.error('no tmpdir')
-                            filename=self.logpath, filemode='a')
+            status = 304
-        if self.path_info != self.APPPATH:
+        elif self.path_info != self.apppath:
+            status = 404
+        else:
+            status = 200
+        self._status = status
+        return status
+
+    def run(self):
+        form = cgi.FieldStorage(self.infp)
+        if self._status != 200:
             self.http_404()
             return
-        if not os.path.isdir(self.tmpdir):
-            logging.error('no tmpdir')
-            self.bummer('error')
-            return
         if (self.method != 'POST' or 
-            'c' not in self.form or
+            'c' not in form or
-            'f' not in self.form):
+            'f' not in form):
             self.coverpage()
             return
-        item = self.form['f']
+        item = form['f']
         if not (item.file and item.filename):
             self.coverpage()
             return
-        cmd = self.form.getvalue('c')
+        cmd = form.getvalue('c')
         html = (cmd == 'Convert to HTML')
         pagenos = []
-        if 'p' in self.form:
+        if 'p' in form:
-            for m in re.finditer(r'\d+', self.form.getvalue('p')):
+            for m in re.finditer(r'\d+', form.getvalue('p')):
                 try:
                     pagenos.append(int(m.group(0)))
                 except ValueError:
                     pass
-        logging.info('received: host=%s, name=%r, pagenos=%r' %
+        self.logger.info('received: host=%s, name=%r, pagenos=%r' %
                          (self.remote_addr, item.filename, pagenos))
         h = abs(hash((random.random(), self.remote_addr, item.filename)))
-        tmppath = os.path.join(self.tmpdir, '%08x%08x.pdf' % (self.cur_time, h))
+        tmppath = os.path.join(self.tmpdir, '%08x%08x.pdf' % (time.time(), h))
         try:
             if not html:
                 self.content_type = 'text/plain; charset=%s' % self.codec
             self.http_200()
             try:
-                convert(sys.stdout, item.file, tmppath, pagenos=pagenos, codec=self.codec,
+                convert(item.file, sys.stdout, tmppath, pagenos=pagenos, codec=self.codec,
                         maxpages=self.MAXPAGES, maxfilesize=self.MAXFILESIZE, html=html)
             except Exception, e:
                 self.put('<p>Sorry, an error has occured: %s' % q(repr(e)))
-                logging.error('convert: %r: path=%r: %s' % (e, tmppath, traceback.format_exc()))
+                self.logger.error('convert: %r: path=%r: %s' % (e, tmppath, traceback.format_exc()))
         finally:
             try:
                 os.remove(tmppath)
@@ -197,4 +202,7 @@ class WebApp(object):
 
 
 # main
-if __name__ == '__main__': sys.exit(WebApp().run(sys.argv))
+if __name__ == '__main__':
+    app = WebApp()
+    app.setup()
+    sys.exit(app.run())