--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/similarity/rcx_gc-ei_ms_subset.msp	Tue Jun 27 14:25:59 2023 +0000
@@ -0,0 +1,288 @@
+NAME: Phenanthrene
+SCANNUMBER: -1
+RETENTIONTIME: -1
+RETENTIONINDEX: 1832.9
+PRECURSORMZ: 178.0775
+PRECURSORTYPE: [M]+
+IONMODE: Positive
+SPECTRUMTYPE: Centroid
+FORMULA: C14H10
+INCHIKEY: YNPNZTXNASCQKK-UHFFFAOYSA-N
+INCHI: 
+SMILES: C1=CC2=C(C=C1)C1=C(C=CC=C1)C=C2
+AUTHORS: Price et al., RECETOX, Masaryk University (CZ)
+COLLISIONENERGY: 70eV
+INSTRUMENT: Q Exactive GC Orbitrap GC-MS/MS
+INSTRUMENTTYPE: GC-EI-Orbitrap
+IONIZATION: EI+
+LICENSE: CC BY-NC
+COMMENT: 
+Num Peaks: 19
+74.01508	137808	"Theoretical m/z 74.01565, Mass diff 0 (0 ppm), Formula C6H2"
+75.02295	278714	"Theoretical m/z 75.023475, Mass diff 0 (0 ppm), Formula C6H3"
+76.03075	608417	"Theoretical m/z 76.0313, Mass diff 0 (0 ppm), Formula C6H4"
+87.02295	304266	"Theoretical m/z 87.023475, Mass diff 0 (0 ppm), Formula C7H3"
+88.03076	497050	"Theoretical m/z 88.0313, Mass diff 0 (0 ppm), Formula C7H4"
+89.03857	441168	"Theoretical m/z 89.039125, Mass diff 0 (0 ppm), Formula C7H5"
+98.01511	150478
+150.04633	868927
+151.05415	546351	"Theoretical m/z 151.054775, Mass diff 0 (0 ppm), Formula C12H7"
+152.0619	2275502
+153.06528	276320
+169.06468	272559
+174.04636	365846
+175.05423	272039	"Theoretical m/z 175.054775, Mass diff 0 (0 ppm), Formula C14H7"
+176.062	3370523	"Theoretical m/z 176.0626, Mass diff 0 (0 ppm), Formula C14H8"
+177.06982	1751846	"Theoretical m/z 177.070425, Mass diff 0 (0 ppm), Formula C14H9"
+178.0775	13724432	"Theoretical m/z 178.077698, Mass diff 0 (1.11 ppm), SMILES C=1C=CC2=C(C1)C=CC=3C=CC=CC32, Annotation [C14H10]+, Rule of HR False"
+179.08078	2250119
+180.08412	138203
+
+NAME: Anthracene
+SCANNUMBER: -1
+RETENTIONTIME: -1
+RETENTIONINDEX: 1844.4
+PRECURSORMZ: 178.07754
+PRECURSORTYPE: [M]+
+IONMODE: Positive
+SPECTRUMTYPE: Centroid
+FORMULA: C14H10
+INCHIKEY: MWPLVEDNUUSJAV-UHFFFAOYSA-N
+INCHI: 
+SMILES: C1=CC2=CC3=C(C=CC=C3)C=C2C=C1
+AUTHORS: Price et al., RECETOX, Masaryk University (CZ)
+COLLISIONENERGY: 70eV
+INSTRUMENT: Q Exactive GC Orbitrap GC-MS/MS
+INSTRUMENTTYPE: GC-EI-Orbitrap
+IONIZATION: EI+
+LICENSE: CC BY-NC
+COMMENT: 
+Num Peaks: 21
+74.0151	117371	"Theoretical m/z 74.01565, Mass diff 0 (0 ppm), Formula C6H2"
+75.02296	245305	"Theoretical m/z 75.023475, Mass diff 0 (0 ppm), Formula C6H3"
+76.03077	632686	"Theoretical m/z 76.0313, Mass diff 0 (0 ppm), Formula C6H4"
+87.02297	236214	"Theoretical m/z 87.023475, Mass diff 0 (0 ppm), Formula C7H3"
+88.03078	347832	"Theoretical m/z 88.0313, Mass diff 0 (0 ppm), Formula C7H4"
+89.0386	507288	"Theoretical m/z 89.039125, Mass diff 0 (0 ppm), Formula C7H5"
+91.05425	130861	"Theoretical m/z 91.054775, Mass diff 0 (0 ppm), Formula C7H7"
+126.04636	128356
+149.04478	126331
+150.04637	641829
+151.05415	403195	"Theoretical m/z 151.054775, Mass diff 0 (0 ppm), Formula C12H7"
+152.06195	1369833
+153.06534	175290
+169.06471	228827
+174.04639	255716
+175.05423	198784	"Theoretical m/z 175.054775, Mass diff 0 (0 ppm), Formula C14H7"
+176.06204	2563053	"Theoretical m/z 176.0626, Mass diff 0 (0 ppm), Formula C14H8"
+177.06984	1182037	"Theoretical m/z 177.070425, Mass diff 0 (0 ppm), Formula C14H9"
+178.07754	11002398	"Theoretical m/z 178.077698, Mass diff 0 (0.89 ppm), SMILES C=1C=CC=2C=C3C=CC=CC3=CC2C1, Annotation [C14H10]+, Rule of HR False"
+179.08081	1778803
+180.08418	132922
+
+NAME: Fluoranthene
+SCANNUMBER: -1
+RETENTIONTIME: -1
+RETENTIONINDEX: 2102.7
+PRECURSORMZ: 202.07756
+PRECURSORTYPE: [M]+
+IONMODE: Positive
+SPECTRUMTYPE: Centroid
+FORMULA: C16H10
+INCHIKEY: GVEPBJHOBDJJJI-UHFFFAOYSA-N
+INCHI: 
+SMILES: C1=CC2=C(C=C1)C1=C3C2=CC=CC3=CC=C1
+AUTHORS: Price et al., RECETOX, Masaryk University (CZ)
+COLLISIONENERGY: 70eV
+INSTRUMENT: Q Exactive GC Orbitrap GC-MS/MS
+INSTRUMENTTYPE: GC-EI-Orbitrap
+IONIZATION: EI+
+LICENSE: CC BY-NC
+COMMENT: 
+Num Peaks: 17
+75.02299	112456	"Theoretical m/z 75.023475, Mass diff 0 (0 ppm), Formula C6H3"
+87.02298	183640	"Theoretical m/z 87.023475, Mass diff 0 (0 ppm), Formula C7H3"
+88.03079	367434	"Theoretical m/z 88.0313, Mass diff 0 (0 ppm), Formula C7H4"
+99.02296	124952	"Theoretical m/z 99.023475, Mass diff 0 (0 ppm), Formula C8H3"
+100.03078	376079
+101.03863	381288	"Theoretical m/z 101.039125, Mass diff 0 (0 ppm), Formula C8H5"
+150.04642	86059
+174.04634	246963
+176.06194	141676	"Theoretical m/z 176.0626, Mass diff 0 (0 ppm), Formula C14H8"
+198.0464	244370
+199.05429	285767	"Theoretical m/z 199.054775, Mass diff 0 (0 ppm), Formula C16H7"
+200.06207	1958890
+201.06982	1103710	"Theoretical m/z 201.070425, Mass diff 0 (0 ppm), Formula C16H9"
+202.07756	8104188	"Theoretical m/z 202.077698, Mass diff 0 (0.69 ppm), SMILES C1=CC=C2C(=C1)C3=CC=CC4=CC=CC2=C43, Annotation [C16H10]+, Rule of HR False"
+203.08084	1377015
+204.08421	98067
+219.08043	186623
+
+NAME: Pyrene
+SCANNUMBER: -1
+RETENTIONTIME: -1
+RETENTIONINDEX: 2154.5
+PRECURSORMZ: 202.07759
+PRECURSORTYPE: [M]+
+IONMODE: Positive
+SPECTRUMTYPE: Centroid
+FORMULA: C16H10
+INCHIKEY: BBEAQIROQSPTKN-UHFFFAOYSA-N
+INCHI: 
+SMILES: C1=CC2=C3C(C=CC4=CC=CC(C=C2)=C34)=C1
+AUTHORS: Price et al., RECETOX, Masaryk University (CZ)
+COLLISIONENERGY: 70eV
+INSTRUMENT: Q Exactive GC Orbitrap GC-MS/MS
+INSTRUMENTTYPE: GC-EI-Orbitrap
+IONIZATION: EI+
+LICENSE: CC BY-NC
+COMMENT: 
+Num Peaks: 16
+87.02299	147113	"Theoretical m/z 87.023475, Mass diff 0 (0 ppm), Formula C7H3"
+88.0308	305149	"Theoretical m/z 88.0313, Mass diff 0 (0 ppm), Formula C7H4"
+99.02298	137042	"Theoretical m/z 99.023475, Mass diff 0 (0 ppm), Formula C8H3"
+100.0308	508914
+101.03864	472094	"Theoretical m/z 101.039125, Mass diff 0 (0 ppm), Formula C8H5"
+101.54032	82430
+150.04637	80741
+174.04631	212706
+198.04643	262925
+199.05429	295144	"Theoretical m/z 199.054775, Mass diff 0 (0 ppm), Formula C16H7"
+200.06209	1960712
+201.06982	1270466	"Theoretical m/z 201.070425, Mass diff 0 (0 ppm), Formula C16H9"
+202.07759	7974712	"Theoretical m/z 202.077698, Mass diff 0 (0.54 ppm), SMILES C=1C=C2C=CC3=CC=CC=4C=CC(C1)=C2C34, Annotation [C16H10]+, Rule of HR False"
+203.08086	1335645
+204.0843	121774
+219.08044	182944
+
+NAME: para-Terphenyl
+SCANNUMBER: -1
+RETENTIONTIME: -1
+RETENTIONINDEX: 2207.5
+PRECURSORMZ: 230.10886
+PRECURSORTYPE: [M]+
+IONMODE: Positive
+SPECTRUMTYPE: Centroid
+FORMULA: C18H14
+INCHIKEY: XJKSTNDFUHDPQJ-UHFFFAOYSA-N
+INCHI: 
+SMILES: C1=CC=C(C=C1)C2=CC=C(C=C2)C3=CC=CC=C3
+AUTHORS: Price et al., RECETOX, Masaryk University (CZ)
+COLLISIONENERGY: 70eV
+INSTRUMENT: Q Exactive GC Orbitrap GC-MS/MS
+INSTRUMENTTYPE: GC-EI-Orbitrap
+IONIZATION: EI+
+LICENSE: CC BY-NC
+COMMENT: 
+Num Peaks: 25
+88.03077	233962	"Theoretical m/z 88.0313, Mass diff 0 (0 ppm), Formula C7H4"
+101.03861	353544	"Theoretical m/z 101.039125, Mass diff 0 (0 ppm), Formula C8H5"
+113.03854	437845	"Theoretical m/z 113.039125, Mass diff 0 (0 ppm), Formula C9H5"
+115.05423	690291	"Theoretical m/z 115.054775, Mass diff 0 (0 ppm), Formula C9H7"
+128.062	293046	"Theoretical m/z 128.0626, Mass diff 0 (0 ppm), Formula C10H8"
+151.05412	266397	"Theoretical m/z 151.054775, Mass diff 0 (0 ppm), Formula C12H7"
+152.06195	961184
+153.06976	409346	"Theoretical m/z 153.069873, Mass diff 0 (0.74 ppm), SMILES *C=1C=CC(=CC1)C=2C=CC=CC2, Annotation [C12H10-H]+, Rule of HR True"
+176.06192	232793	"Theoretical m/z 176.0626, Mass diff 0 (0 ppm), Formula C14H8"
+189.06972	408734	"Theoretical m/z 189.070425, Mass diff 0 (0 ppm), Formula C15H9"
+200.0619	342984
+201.06986	238974	"Theoretical m/z 201.070425, Mass diff 0 (0 ppm), Formula C16H9"
+202.07758	1292332
+203.08093	374439
+213.06973	256631	"Theoretical m/z 213.070425, Mass diff 0 (0 ppm), Formula C17H9"
+215.08548	1220866	"Theoretical m/z 215.086075, Mass diff 0 (0 ppm), Formula C17H11"
+216.08881	217320
+224.062	181393
+226.07771	1503774
+227.08588	1198323	"Theoretical m/z 227.086075, Mass diff 0 (0 ppm), Formula C18H11"
+228.09344	2885510
+229.10123	1791323
+230.10886	17890056	"Theoretical m/z 230.108994, Mass diff 0 (0.58 ppm), SMILES C=1C=CC(=CC1)C=2C=CC(=CC2)C=3C=CC=CC3, Annotation [C18H14]+, Rule of HR False"
+231.11214	3536976
+232.11542	320231
+
+NAME: Benzo[b]naphtho[2,1-d]thiophene
+SCANNUMBER: -1
+RETENTIONTIME: -1
+RETENTIONINDEX: 2419.3
+PRECURSORMZ: 234.04965
+PRECURSORTYPE: [M]+
+IONMODE: Positive
+SPECTRUMTYPE: Centroid
+FORMULA: C16H10S
+INCHIKEY: YEUHHUCOSQOCIX-UHFFFAOYSA-N
+INCHI: 
+SMILES: S1C2=C(C=CC=C2)C2=C1C1=CC=CC=C1C=C2
+AUTHORS: Price et al., RECETOX, Masaryk University (CZ)
+COLLISIONENERGY: 70eV
+INSTRUMENT: Q Exactive GC Orbitrap GC-MS/MS
+INSTRUMENTTYPE: GC-EI-Orbitrap
+IONIZATION: EI+
+LICENSE: CC BY-NC
+COMMENT: 
+Num Peaks: 23
+91.05425	49130	"Theoretical m/z 91.054775, Mass diff 0 (0 ppm), Formula C7H7"
+93.52686	61653
+94.53469	76638
+104.01679	126871
+116.01675	112547
+117.02459	99108
+162.04623	54491
+163.05408	136418	"Theoretical m/z 163.054775, Mass diff 0 (0 ppm), Formula C13H7"
+164.06198	56321
+187.05406	273349	"Theoretical m/z 187.054775, Mass diff 0 (0 ppm), Formula C15H7"
+188.06189	200750
+189.06969	453336	"Theoretical m/z 189.070425, Mass diff 0 (0 ppm), Formula C15H9"
+190.07306	77884
+200.06189	135620
+201.06973	74692	"Theoretical m/z 201.070425, Mass diff 0 (0 ppm), Formula C16H9"
+202.07758	425058
+203.08086	72058
+226.07762	63460
+232.03409	769638
+233.04245	382457	"Theoretical m/z 233.042496, Mass diff -0.001 (0 ppm), Formula C16H9S"
+234.04965	4404102	"Theoretical m/z 234.049775, Mass diff 0 (0.53 ppm), SMILES S1C=2C=CC=CC2C=3C=CC=4C=CC=CC4C13, Annotation [C16H10S]+, Rule of HR False"
+235.05304	725574
+236.04547	251450
+
+NAME: 2,3-Benzofluorene
+SCANNUMBER: -1
+RETENTIONTIME: -1
+RETENTIONINDEX: 2257.5
+PRECURSORMZ: 216.09326
+PRECURSORTYPE: [M]+
+IONMODE: Positive
+SPECTRUMTYPE: Centroid
+FORMULA: C17H12
+INCHIKEY: HAPOJKSPCGLOOD-UHFFFAOYSA-N
+INCHI: 
+SMILES: C1C2=CC=CC=C2C2=C1C=C1C=CC=CC1=C2
+AUTHORS: Price et al., RECETOX, Masaryk University (CZ)
+COLLISIONENERGY: 70eV
+INSTRUMENT: Q Exactive GC Orbitrap GC-MS/MS
+INSTRUMENTTYPE: GC-EI-Orbitrap
+IONIZATION: EI+
+LICENSE: CC BY-NC
+COMMENT: 
+Num Peaks: 21
+93.52689	122035
+94.53471	241743
+95.03638	42130
+105.52688	47526
+106.53471	171653
+107.03639	60004
+107.5425	180288
+108.03385	97471
+163.05414	68194	"Theoretical m/z 163.054775, Mass diff 0 (0 ppm), Formula C13H7"
+187.05412	167183	"Theoretical m/z 187.054775, Mass diff 0 (0 ppm), Formula C15H7"
+188.06201	86262
+189.06975	239421	"Theoretical m/z 189.070425, Mass diff 0 (0 ppm), Formula C15H9"
+190.07321	37778
+211.05426	117044	"Theoretical m/z 211.054775, Mass diff 0 (0 ppm), Formula C17H7"
+212.06215	60813
+213.0699	808499	"Theoretical m/z 213.070425, Mass diff 0 (0 ppm), Formula C17H9"
+214.07317	202222
+215.0855	3634570	"Theoretical m/z 215.086075, Mass diff 0 (0 ppm), Formula C17H11"
+216.09326	2535030	"Theoretical m/z 216.093354, Mass diff 0 (0.44 ppm), SMILES C=1C=CC=2C=C3C(=CC2C1)C=4C=CC=CC4C3, Annotation [C17H12]+, Rule of HR False"
+217.09671	444170
+218.09999	37976