Commit 243dcf76 authored by Vít Novotný's avatar Vít Novotný
Browse files

Add ARQMath formulae V1.0

parent 239f0638

output_data/ARQMath_CLEF2020/Formulas/.gitignore

+12 −12
Original line number Diff line number Diff line 
/formula_opt.V0.2.tsv

/formula_opt.V0.2.failures

/formula_prefix.V0.2.tsv

/formula_prefix.V0.2.failures

/formula_slt.V0.2.tsv

/formula_slt.V0.2.failures

/formula_cmml.V0.2.tsv

/formula_cmml.V0.2.failures

/formula_pmml.V0.2.tsv

/formula_pmml.V0.2.failures

/formula_infix.V0.2.tsv

/formula_infix.V0.2.failures
 
/formula_opt.V1.0.tsv

/formula_opt.V1.0.failures

/formula_prefix.V1.0.tsv

/formula_prefix.V1.0.failures

/formula_slt.V1.0.tsv

/formula_slt.V1.0.failures

/formula_cmml.V1.0.tsv

/formula_cmml.V1.0.failures

/formula_pmml.V1.0.tsv

/formula_pmml.V1.0.failures

/formula_infix.V1.0.tsv

/formula_infix.V1.0.failures

output_data/ARQMath_CLEF2020/Formulas/Makefile

+14 −14
Original line number Diff line number Diff line
@@ -2,23 +2,23 @@ 


RUN_SCRIPT=cd ../../.. && python3 -m



CMML=formula_cmml.V0.2.tsv

PMML=formula_pmml.V0.2.tsv

OPT=formula_opt.V0.2.tsv

SLT=formula_slt.V0.2.tsv

PREFIX=formula_prefix.V0.2.tsv

INFIX=formula_infix.V0.2.tsv



sanity-check:

	grep -P '^14047452\t' $(CMML)   | grep -q '<cn [^>]*>3'

	grep -P '^14047452\t' $(PMML)   | grep -q '<mn [^>]*>3'

	grep -P '^14047452\t' $(OPT)    | grep -q 'N!3'

	grep -P '^14047452\t' $(SLT)    | grep -q 'N!3'

	grep -P '^14047452\t' $(PREFIX) | grep -q 'N!3'

	grep -P '^14047452\t' $(INFIX)  | grep -q 'N!3'

CMML=formula_cmml.V1.0.tsv

PMML=formula_pmml.V1.0.tsv

OPT=formula_opt.V1.0.tsv

SLT=formula_slt.V1.0.tsv

PREFIX=formula_prefix.V1.0.tsv

INFIX=formula_infix.V1.0.tsv



all: $(CMML) $(PMML) $(OPT) $(SLT) $(PREFIX) $(INFIX)



sanity-check:

	grep -P -A 1 '^14047452\t' $(CMML)   | grep -q '<ci [^>]*>S<\/ci>'

	grep -P -A 1 '^14047452\t' $(PMML)   | grep -q '<mi [^>]*>S<\/mi>'

	grep -P      '^14047452\t' $(OPT)    | grep -q 'V!S'

	grep -P      '^14047452\t' $(SLT)    | grep -q 'V!S'

	grep -P      '^14047452\t' $(PREFIX) | grep -q 'V!S'

	grep -P      '^14047452\t' $(INFIX)  | grep -q 'V!S'



$(CMML) $(PMML):

	$(RUN_SCRIPT) scripts.latex_tsv_to_cmml_and_pmml_tsv train

output_data/ARQMath_CLEF2020/Formulas/formula_cmml_and_pmml.V0.2.tsv.dvc→output_data/ARQMath_CLEF2020/Formulas/formula_cmml_and_pmml.V1.0.tsv.dvc

+23 −0
Original line number Diff line number Diff line 
cmd: make formula_cmml.V0.2.tsv

cmd: make formula_cmml.V1.0.tsv

outs:

- path: formula_cmml.V0.2.failures

- path: formula_cmml.V1.0.failures

  persist: false

  md5: 1659b05383f7be69651673b6d95fc675

  md5: ab7c8c9c63907b756a8f57b04871eca2

  metric: false

  cache: true

- path: formula_cmml.V0.2.tsv

- path: formula_cmml.V1.0.tsv

  persist: false

  md5: d30342f1fa64db69dc148f9a338e8f95

  md5: 135c4d2823d77c116fbef534c23b58a7

  metric: false

  cache: true

- path: formula_pmml.V0.2.failures

- path: formula_pmml.V1.0.failures

  persist: false

  md5: 9f5de2d848d2274fa8040dfecbe87a71

  md5: ef801e5c752089106d708f920399c30c

  metric: false

  cache: true

- path: formula_pmml.V0.2.tsv

- path: formula_pmml.V1.0.tsv

  persist: false

  md5: 38ddfa8e934e93cd49ce37f3fa7a77b7

  md5: 3bc08f8609ffaa6aa0cfc672ab2cb6ae

  metric: false

  cache: true

md5: 6fb1a335e8ac1fc4e13ee74e3d12aca6
 
md5: 3849e5af3c1dcb26eacbe83122a7f4d7

output_data/ARQMath_CLEF2020/Formulas/formula_infix.V0.2.tsv.dvc

deleted100644 → 0
+0 −16
Original line number Diff line number Diff line 
md5: 54a93eb637af17446c14346dd53e53e8

outs:

- metric: false

  md5: 6f098c9de3a8ffcacde5b5ab49758243

  cache: true

  persist: false

  path: formula_infix.V0.2.tsv

- metric: false

  md5: 2f4bcc28a819df0a7cd4f8034fcad522

  cache: true

  persist: false

  path: formula_infix.V0.2.failures

deps:

- md5: d30342f1fa64db69dc148f9a338e8f95

  path: formula_cmml.V0.2.tsv

cmd: make formula_infix.V0.2.tsv

output_data/ARQMath_CLEF2020/Formulas/formula_infix.V1.0.tsv.dvc

0 → 100644
+16 −0
Original line number Diff line number Diff line 
md5: 68e173c2daf5eb69d70e37ff72c4e4be

outs:

- metric: false

  md5: 41dd59f2f8a650df2336c0943ab4b019

  cache: true

  persist: false

  path: formula_infix.V1.0.tsv

- metric: false

  md5: 345d08809e898f6e6fb73225a1f19ef3

  cache: true

  persist: false

  path: formula_infix.V1.0.failures

deps:

- md5: 135c4d2823d77c116fbef534c23b58a7

  path: formula_cmml.V1.0.tsv

cmd: make formula_infix.V1.0.tsv