diff --git a/data/cif-core.csv b/data/cif-core.csv
new file mode 100644
index 0000000000000000000000000000000000000000..25ce0320c9e0e7c60a833309094d6a27814b7a4c
--- /dev/null
+++ b/data/cif-core.csv
@@ -0,0 +1,60 @@
+audit.block_doi
+
+database_code.depnum_ccdc_archive
+
+chemical.name_systematic
+chemical.name_common
+chemical.melting_point
+
+chemical_formula.moiety
+chemical_formula.sum
+chemical_formula.weight
+
+atom_type.symbol
+atom_type.description
+
+atom_type_scat.dispersion_real
+atom_type_scat.dispersion_imag
+atom_type_scat.source
+
+space_group.crystal_system
+space_group.name_H-M_full
+space_group_symop.operation_xyz
+
+cell.length_a
+cell.length_b
+cell.length_c
+cell.angle_alpha
+cell.angle_beta
+cell.angle_gamma
+cell.volume
+cell.formula_units_Z
+
+atom_site.label
+atom_site.type_symbol
+atom_site.fract_x
+atom_site.fract_y
+atom_site.fract_z
+atom_site.U_iso_or_equiv
+atom_site.adp_type
+atom_site.occupancy
+atom_site.calc_flag
+atom_site.refinement_flags
+atom_site.disorder_assembly
+atom_site.disorder_group
+
+atom_site.site_symmetry_multiplicity
+
+atom_site_aniso.label
+atom_site_aniso.U_11
+atom_site_aniso.U_22
+atom_site_aniso.U_33
+atom_site_aniso.U_23
+atom_site_aniso.U_13
+atom_site_aniso.U_12
+
+geom_bond.atom_site_label_1
+geom_bond.atom_site_label_2
+geom_bond.distance
+geom_bond.site_symmetry_2
+geom_bond.publ_flag
\ No newline at end of file
diff --git a/examples/867861-core.cif b/examples/867861-core.cif
new file mode 100644
index 0000000000000000000000000000000000000000..aa77d962c74517ca7f4d83f5e008ad91c0cbe490
--- /dev/null
+++ b/examples/867861-core.cif
@@ -0,0 +1,884 @@
+#######################################################################
+#
+# This file contains crystal structure data downloaded from the
+# Cambridge Structural Database (CSD) hosted by the Cambridge
+# Crystallographic Data Centre (CCDC).
+#
+# Full information about CCDC data access policies and citation
+# guidelines are available at http://www.ccdc.cam.ac.uk/access/V1
+#
+# Audit and citation data items may have been added by the CCDC.
+# Please retain this information to preserve the provenance of
+# this file and to allow appropriate attribution of the data.
+#
+#######################################################################
+
+data_n1379
+_audit_block_doi 10.5517/ccy42jn
+_database_code_depnum_ccdc_archive 'CCDC 867861'
+loop_
+_citation_id
+_citation_doi
+_citation_year
+1 10.1002/chem.201202070 2012
+_audit_update_record
+;
+2012-02-20 deposited with the CCDC.
+2016-10-08 downloaded from the CCDC.
+;
+
+_audit_creation_method SHELXL-97
+_chemical_name_systematic
+;
+?
+;
+_chemical_name_common ?
+_chemical_melting_point ?
+_chemical_formula_moiety 'C76 H90 N10 O14 4(C2 F3 O2) 4(C2 H3 N)'
+_chemical_formula_sum 'C92 H102 F12 N14 O22'
+_chemical_formula_weight 1983.88
+
+loop_
+_atom_type_symbol
+_atom_type_description
+_atom_type_scat_dispersion_real
+_atom_type_scat_dispersion_imag
+_atom_type_scat_source
+C C 0.0181 0.0091 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+H H 0.0000 0.0000 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+N N 0.0311 0.0180 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+O O 0.0492 0.0322 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+F F 0.0727 0.0534 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+
+_symmetry_cell_setting Triclinic
+_symmetry_space_group_name_H-M P-1
+
+loop_
+_symmetry_equiv_pos_as_xyz
+'x, y, z'
+'-x, -y, -z'
+
+_cell_length_a 11.0829(8)
+_cell_length_b 14.6829(10)
+_cell_length_c 16.8532(17)
+_cell_angle_alpha 105.728(6)
+_cell_angle_beta 100.310(6)
+_cell_angle_gamma 110.620(4)
+_cell_volume 2353.3(3)
+_cell_formula_units_Z 1
+_cell_measurement_temperature 100(2)
+_cell_measurement_reflns_used 5934
+_cell_measurement_theta_min 2.86
+_cell_measurement_theta_max 64.30
+
+_exptl_crystal_description plate
+_exptl_crystal_colour violet
+_exptl_crystal_size_max 0.57
+_exptl_crystal_size_mid 0.18
+_exptl_crystal_size_min 0.05
+_exptl_crystal_density_meas ?
+_exptl_crystal_density_diffrn 1.400
+_exptl_crystal_density_method ?
+_exptl_crystal_F_000 1036
+_exptl_absorpt_coefficient_mu 0.995
+_exptl_absorpt_correction_type integration
+_exptl_absorpt_correction_T_min 0.6022
+_exptl_absorpt_correction_T_max 0.9482
+_exptl_absorpt_process_details 'XPREP, face-indexed'
+
+_exptl_special_details
+;
+?
+;
+
+_diffrn_ambient_temperature 100(2)
+_diffrn_radiation_wavelength 1.54178
+_diffrn_radiation_type CuK\a
+_diffrn_radiation_source microsource
+_diffrn_radiation_monochromator 'Quazar optics'
+_diffrn_measurement_device_type 'Bruker APEX-II CCD'
+_diffrn_measurement_method '\f and \w scans'
+_diffrn_detector_area_resol_mean ?
+_diffrn_reflns_number 16613
+_diffrn_reflns_av_R_equivalents 0.1477
+_diffrn_reflns_av_sigmaI/netI 0.1112
+_diffrn_reflns_limit_h_min -12
+_diffrn_reflns_limit_h_max 8
+_diffrn_reflns_limit_k_min -17
+_diffrn_reflns_limit_k_max 17
+_diffrn_reflns_limit_l_min -19
+_diffrn_reflns_limit_l_max 19
+_diffrn_reflns_theta_min 2.86
+_diffrn_reflns_theta_max 64.94
+_reflns_number_total 7680
+_reflns_number_gt 5560
+_reflns_threshold_expression >2sigma(I)
+
+_computing_data_collection 'Bruker APEX2'
+_computing_cell_refinement 'Bruker SAINT'
+_computing_data_reduction 'Bruker SAINT'
+_computing_structure_solution 'SHELXS-97 (Sheldrick, 2008)'
+_computing_structure_refinement 'SHELXL-97 (Sheldrick, 2008)'
+_computing_molecular_graphics 'Bruker SHELXTL'
+_computing_publication_material 'Bruker SHELXTL'
+
+_refine_special_details
+;
+Refinement of F^2^ against ALL reflections. The weighted R-factor wR and
+goodness of fit S are based on F^2^, conventional R-factors R are based
+on F, with F set to zero for negative F^2^. The threshold expression of
+F^2^ > 2sigma(F^2^) is used only for calculating R-factors(gt) etc. and is
+not relevant to the choice of reflections for refinement. R-factors based
+on F^2^ are statistically about twice as large as those based on F, and R-
+factors based on ALL data will be even larger.
+Rigid bond restraints (esd 0.002) were imposed on the displacement parameters,
+as well as restraints on similar amplitudes (esd 0.002) separated by less
+than 1.7 Ang. on C27, C29, and N102.
+Distance restraints were refined on the bond between C28 and C29.
+;
+
+_refine_ls_structure_factor_coef Fsqd
+_refine_ls_matrix_type full
+_refine_ls_weighting_scheme calc
+_refine_ls_weighting_details
+'calc w=1/[\s^2^(Fo^2^)+(0.1912P)^2^+4.8134P] where P=(Fo^2^+2Fc^2^)/3'
+_atom_sites_solution_primary direct
+_atom_sites_solution_secondary difmap
+_atom_sites_solution_hydrogens geom
+_refine_ls_hydrogen_treatment mixed
+_refine_ls_extinction_method none
+_refine_ls_extinction_coef ?
+_refine_ls_number_reflns 7680
+_refine_ls_number_parameters 633
+_refine_ls_number_restraints 1
+_refine_ls_R_factor_all 0.1349
+_refine_ls_R_factor_gt 0.1101
+_refine_ls_wR_factor_ref 0.3402
+_refine_ls_wR_factor_gt 0.3102
+_refine_ls_goodness_of_fit_ref 1.089
+_refine_ls_restrained_S_all 1.096
+_refine_ls_shift/su_max 0.000
+_refine_ls_shift/su_mean 0.000
+
+loop_
+_atom_site_label
+_atom_site_type_symbol
+_atom_site_fract_x
+_atom_site_fract_y
+_atom_site_fract_z
+_atom_site_U_iso_or_equiv
+_atom_site_adp_type
+_atom_site_occupancy
+_atom_site_symmetry_multiplicity
+_atom_site_calc_flag
+_atom_site_refinement_flags
+_atom_site_disorder_assembly
+_atom_site_disorder_group
+C1 C -0.3373(4) -0.2086(3) -0.2547(3) 0.0229(10) Uani 1 1 d . . .
+H1 H -0.3820 -0.2827 -0.2795 0.027 Uiso 1 1 calc R . .
+C2 C -0.1956(4) -0.0511(3) -0.2602(3) 0.0215(10) Uani 1 1 d . . .
+H2 H -0.1401 -0.0147 -0.2886 0.026 Uiso 1 1 calc R . .
+C3 C -0.3583(4) -0.1574(3) -0.1814(3) 0.0213(9) Uani 1 1 d . . .
+H3 H -0.4168 -0.1960 -0.1558 0.026 Uiso 1 1 calc R . .
+C4 C -0.2146(4) 0.0039(3) -0.1873(3) 0.0180(9) Uani 1 1 d . . .
+H4 H -0.1736 0.0780 -0.1660 0.022 Uiso 1 1 calc R . .
+C5 C -0.2943(4) -0.0488(3) -0.1440(3) 0.0163(9) Uani 1 1 d . . .
+C6 C -0.3053(4) 0.0091(3) -0.0600(3) 0.0170(9) Uani 1 1 d . . .
+C7 C -0.3538(4) -0.0444(3) -0.0071(3) 0.0193(9) Uani 1 1 d . . .
+H7 H -0.3850 -0.1181 -0.0264 0.023 Uiso 1 1 calc R . .
+C8 C -0.2620(4) 0.1168(3) -0.0291(3) 0.0194(9) Uani 1 1 d . . .
+H8 H -0.2304 0.1553 -0.0640 0.023 Uiso 1 1 calc R . .
+C9 C -0.3563(4) 0.0094(3) 0.0725(3) 0.0218(10) Uani 1 1 d . . .
+H9 H -0.3904 -0.0276 0.1077 0.026 Uiso 1 1 calc R . .
+C10 C -0.2648(4) 0.1679(3) 0.0515(3) 0.0190(9) Uani 1 1 d . . .
+H10 H -0.2340 0.2416 0.0724 0.023 Uiso 1 1 calc R . .
+C11 C -0.3024(4) 0.1707(4) 0.1919(3) 0.0227(10) Uani 1 1 d . . .
+H11A H -0.3772 0.1277 0.2088 0.027 Uiso 1 1 calc R . .
+H11B H -0.3094 0.2371 0.1964 0.027 Uiso 1 1 calc R . .
+C12 C -0.1670(4) 0.1920(3) 0.2509(2) 0.0184(9) Uani 1 1 d . . .
+C13 C -0.1547(5) 0.1179(4) 0.2849(3) 0.0223(10) Uani 1 1 d . . .
+H13 H -0.2328 0.0589 0.2788 0.027 Uiso 1 1 calc R . .
+C14 C -0.0541(4) 0.2821(3) 0.2667(2) 0.0204(9) Uani 1 1 d . . .
+H14 H -0.0631 0.3352 0.2475 0.024 Uiso 1 1 calc R . .
+C15 C -0.0272(5) 0.1313(4) 0.3277(3) 0.0231(10) Uani 1 1 d . . .
+H15 H -0.0192 0.0806 0.3506 0.028 Uiso 1 1 calc R . .
+C16 C 0.0731(4) 0.2946(3) 0.3110(2) 0.0195(9) Uani 1 1 d . . .
+C17 C 0.0890(4) 0.2163(3) 0.3381(2) 0.0204(10) Uani 1 1 d . . .
+C18 C 0.2252(5) 0.2149(4) 0.3687(3) 0.0273(11) Uani 1 1 d . . .
+H18A H 0.2965 0.2872 0.3968 0.033 Uiso 1 1 calc R . .
+H18B H 0.2237 0.1802 0.4116 0.033 Uiso 1 1 calc R . .
+C19 C 0.2862(4) 0.4582(4) 0.3974(3) 0.0247(10) Uani 1 1 d . . .
+H19 H 0.3032 0.4532 0.4530 0.030 Uiso 1 1 calc R . .
+C20 C 0.3577(5) 0.5371(4) 0.3739(3) 0.0279(11) Uani 1 1 d . . .
+C21 C 0.4805(5) 0.6358(4) 0.4267(3) 0.0333(12) Uani 1 1 d . . .
+H21A H 0.4882 0.6869 0.3975 0.040 Uiso 1 1 calc R . .
+H21B H 0.4699 0.6656 0.4837 0.040 Uiso 1 1 calc R . .
+C22 C 0.6303(6) 0.5857(4) 0.3599(3) 0.0374(12) Uani 1 1 d . . .
+H22A H 0.6523 0.6416 0.3355 0.045 Uiso 1 1 calc R . .
+H22B H 0.5494 0.5242 0.3176 0.045 Uiso 1 1 calc R . .
+C23 C 0.7460(6) 0.5575(5) 0.3762(4) 0.0413(13) Uani 1 1 d . . .
+H23A H 0.7730 0.5406 0.3231 0.050 Uiso 1 1 calc R . .
+H23B H 0.8246 0.6169 0.4226 0.050 Uiso 1 1 calc R . .
+C24 C 0.7952(6) 0.4206(5) 0.3967(4) 0.0496(16) Uani 1 1 d . . .
+H24A H 0.8893 0.4743 0.4264 0.060 Uiso 1 1 calc R . .
+H24B H 0.7870 0.3874 0.3353 0.060 Uiso 1 1 calc R . .
+C25 C 0.7663(11) 0.3428(7) 0.4361(4) 0.074(3) Uani 1 1 d . . .
+H25A H 0.8372 0.3165 0.4378 0.089 Uiso 1 1 calc R . .
+H25B H 0.7691 0.3754 0.4965 0.089 Uiso 1 1 calc R . .
+C26 C 0.6441(8) 0.1838(7) 0.4342(5) 0.071(2) Uani 1 1 d . . .
+H26A H 0.7153 0.1600 0.4249 0.085 Uiso 1 1 calc R . .
+H26B H 0.6577 0.2137 0.4970 0.085 Uiso 1 1 calc R . .
+C27 C 0.5204(10) 0.1080(8) 0.3921(7) 0.125(5) Uani 1 1 d . . .
+H27A H 0.5220 0.0408 0.3913 0.150 Uiso 1 1 calc R . .
+H27B H 0.4964 0.1039 0.3313 0.150 Uiso 1 1 calc R . .
+C28 C 0.3730(9) 0.0886(7) 0.4988(5) 0.097(4) Uani 1 1 d D . .
+H28A H 0.4284 0.0506 0.5097 0.116 Uiso 1 1 calc R . .
+H28B H 0.4078 0.1526 0.5510 0.116 Uiso 1 1 calc R . .
+C29 C 0.2559(11) 0.033(2) 0.4964(8) 0.281(16) Uani 1 1 d D . .
+H29A H 0.2452 0.0690 0.5518 0.337 Uiso 1 1 calc R . .
+H29B H 0.2589 -0.0322 0.5000 0.337 Uiso 1 1 calc R . .
+C30 C 0.0569(12) -0.1026(9) 0.4169(5) 0.089(3) Uani 1 1 d . . .
+H30A H 0.0442 -0.1134 0.4708 0.107 Uiso 1 1 calc R . .
+H30B H 0.1035 -0.1448 0.3928 0.107 Uiso 1 1 calc R . .
+C31 C -0.0702(10) -0.1360(6) 0.3569(6) 0.083(3) Uani 1 1 d . . .
+H31A H -0.1307 -0.2064 0.3530 0.100 Uiso 1 1 calc R . .
+H31B H -0.1113 -0.0878 0.3776 0.100 Uiso 1 1 calc R . .
+C32 C -0.1964(9) -0.1774(5) 0.2168(5) 0.067(2) Uani 1 1 d . . .
+H32A H -0.2564 -0.2441 0.2195 0.080 Uiso 1 1 calc R . .
+H32B H -0.2342 -0.1258 0.2343 0.080 Uiso 1 1 calc R . .
+C33 C -0.1881(7) -0.1926(5) 0.1297(4) 0.0593(19) Uani 1 1 d . . .
+H33A H -0.2803 -0.2327 0.0880 0.071 Uiso 1 1 calc R . .
+H33B H -0.1354 -0.2340 0.1169 0.071 Uiso 1 1 calc R . .
+C34 C -0.0909(4) -0.0989(4) 0.0440(3) 0.0231(10) Uani 1 1 d . . .
+C35 C -0.1178(5) -0.1907(4) -0.0206(3) 0.0290(11) Uani 1 1 d . . .
+H35 H -0.1660 -0.2560 -0.0162 0.035 Uiso 1 1 calc R . .
+C36 C -0.0214(4) -0.0005(3) 0.0371(3) 0.0182(9) Uani 1 1 d . . .
+C37 C 0.0055(4) 0.0950(3) 0.1019(3) 0.0212(10) Uani 1 1 d . . .
+H37 H -0.0240 0.0948 0.1515 0.025 Uiso 1 1 calc R . .
+C38 C 0.0734(4) 0.1868(4) 0.0931(3) 0.0249(10) Uani 1 1 d . . .
+H38 H 0.0914 0.2503 0.1372 0.030 Uiso 1 1 calc R . .
+N1 N -0.2553(3) -0.1567(3) -0.2921(2) 0.0202(8) Uani 1 1 d . . .
+N2 N -0.3112(3) 0.1137(3) 0.1013(2) 0.0181(8) Uani 1 1 d . . .
+N3 N 0.1854(4) 0.3880(3) 0.3242(2) 0.0221(8) Uani 1 1 d . . .
+N4 N 0.1947(4) 0.4236(3) 0.2574(2) 0.0281(9) Uani 1 1 d . . .
+N5 N 0.2991(4) 0.5136(3) 0.2881(3) 0.0315(10) Uani 1 1 d . . .
+O1 O 0.6028(3) 0.6210(3) 0.4395(2) 0.0301(8) Uani 1 1 d . . .
+O2 O 0.7045(4) 0.4689(3) 0.4018(2) 0.0429(10) Uani 1 1 d . . .
+O3 O 0.6381(7) 0.2580(4) 0.3907(4) 0.0743(17) Uani 1 1 d . . .
+O4 O 0.4041(4) 0.1218(3) 0.4321(2) 0.0412(10) Uani 1 1 d . . .
+O5 O 0.1363(5) 0.0023(6) 0.4355(3) 0.0786(19) Uani 1 1 d . . .
+O6 O -0.0597(6) -0.1394(4) 0.2749(3) 0.0757(17) Uani 1 1 d . . .
+O7 O -0.1244(3) -0.0939(3) 0.1185(2) 0.0320(8) Uani 1 1 d . . .
+C101 C 0.6294(5) 0.3676(4) 0.1211(3) 0.0286(11) Uani 1 1 d . . .
+C102 C 0.5798(8) 0.4458(5) 0.1022(5) 0.066(2) Uani 1 1 d . . .
+C103 C 0.5077(5) 0.8961(4) 0.2466(3) 0.0342(12) Uani 1 1 d . . .
+C104 C 0.3819(8) 0.8078(6) 0.2433(5) 0.077(3) Uani 1 1 d . . .
+C105 C 0.0707(7) 0.4215(5) 0.0313(4) 0.0516(16) Uani 1 1 d . . .
+C106 C 0.2104(7) 0.4969(6) 0.0645(5) 0.066(2) Uani 1 1 d . . .
+H10A H 0.2627 0.4718 0.0303 0.099 Uiso 1 1 calc R . .
+H10B H 0.2471 0.5066 0.1251 0.099 Uiso 1 1 calc R . .
+H10C H 0.2161 0.5637 0.0606 0.099 Uiso 1 1 calc R . .
+C107 C 0.0569(7) 0.6249(7) 0.2999(5) 0.071(2) Uani 1 1 d . . .
+C108 C 0.0316(8) 0.5978(7) 0.2128(5) 0.077(2) Uani 1 1 d . . .
+H10D H 0.0994 0.5753 0.1954 0.115 Uiso 1 1 calc R . .
+H10E H 0.0360 0.6581 0.1969 0.115 Uiso 1 1 calc R . .
+H10F H -0.0588 0.5404 0.1833 0.115 Uiso 1 1 calc R . .
+O101 O 0.5421(4) 0.2774(3) 0.0882(3) 0.0463(10) Uani 1 1 d . . .
+O102 O 0.7472(4) 0.4014(3) 0.1666(3) 0.0485(11) Uani 1 1 d . . .
+O103 O 0.4882(4) 0.9389(3) 0.1955(2) 0.0356(9) Uani 1 1 d . . .
+O104 O 0.6107(4) 0.9176(3) 0.3029(3) 0.0517(11) Uani 1 1 d . . .
+F101 F 0.4877(8) 0.4530(7) 0.1408(4) 0.148(3) Uani 1 1 d . . .
+F102 F 0.5188(6) 0.4177(4) 0.0191(3) 0.105(2) Uani 1 1 d . . .
+F103 F 0.6733(8) 0.5407(3) 0.1298(5) 0.160(4) Uani 1 1 d . . .
+F104 F 0.2811(5) 0.7655(4) 0.1734(3) 0.098(2) Uani 1 1 d . . .
+F105 F 0.3328(8) 0.8406(9) 0.3070(4) 0.233(7) Uani 1 1 d . . .
+F106 F 0.4002(9) 0.7351(6) 0.2617(7) 0.224(6) Uani 1 1 d . . .
+N101 N -0.0392(7) 0.3613(5) 0.0045(4) 0.0715(19) Uani 1 1 d . . .
+N102 N 0.0774(10) 0.6479(13) 0.3716(6) 0.185(7) Uani 1 1 d . . .
+
+loop_
+_atom_site_aniso_label
+_atom_site_aniso_U_11
+_atom_site_aniso_U_22
+_atom_site_aniso_U_33
+_atom_site_aniso_U_23
+_atom_site_aniso_U_13
+_atom_site_aniso_U_12
+C1 0.015(2) 0.023(2) 0.022(2) -0.0003(18) -0.0032(18) 0.0097(17)
+C2 0.021(2) 0.032(2) 0.012(2) 0.0047(17) -0.0022(17) 0.0168(19)
+C3 0.0099(19) 0.030(2) 0.021(2) 0.0059(18) -0.0007(17) 0.0104(17)
+C4 0.017(2) 0.027(2) 0.0111(19) 0.0045(16) -0.0012(16) 0.0157(18)
+C5 0.0087(18) 0.025(2) 0.0134(19) 0.0028(16) -0.0032(15) 0.0121(16)
+C6 0.0075(18) 0.031(2) 0.014(2) 0.0067(17) -0.0017(15) 0.0130(17)
+C7 0.0074(18) 0.029(2) 0.019(2) 0.0047(17) 0.0003(16) 0.0093(17)
+C8 0.0135(19) 0.028(2) 0.013(2) 0.0039(17) -0.0035(16) 0.0120(17)
+C9 0.013(2) 0.031(2) 0.020(2) 0.0072(18) 0.0012(17) 0.0105(18)
+C10 0.0112(19) 0.029(2) 0.018(2) 0.0066(17) 0.0025(16) 0.0122(17)
+C11 0.019(2) 0.038(2) 0.014(2) 0.0056(18) 0.0059(17) 0.0178(19)
+C12 0.019(2) 0.029(2) 0.0068(18) -0.0007(16) 0.0013(16) 0.0169(18)
+C13 0.024(2) 0.030(2) 0.013(2) 0.0023(17) 0.0047(18) 0.0159(19)
+C14 0.027(2) 0.027(2) 0.0079(19) -0.0015(16) 0.0012(17) 0.0200(19)
+C15 0.030(2) 0.034(2) 0.012(2) 0.0056(17) 0.0059(18) 0.023(2)
+C16 0.023(2) 0.028(2) 0.0057(18) -0.0018(16) 0.0027(16) 0.0154(19)
+C17 0.024(2) 0.032(2) 0.0063(18) -0.0012(16) 0.0008(16) 0.0209(19)
+C18 0.028(2) 0.040(3) 0.010(2) -0.0024(18) -0.0038(18) 0.025(2)
+C19 0.023(2) 0.034(2) 0.012(2) -0.0015(18) -0.0024(17) 0.017(2)
+C20 0.024(2) 0.031(2) 0.019(2) 0.0008(19) -0.0030(19) 0.011(2)
+C21 0.027(3) 0.034(3) 0.028(3) -0.001(2) 0.001(2) 0.014(2)
+C22 0.038(3) 0.046(3) 0.027(3) 0.011(2) 0.010(2) 0.018(2)
+C23 0.039(3) 0.054(3) 0.033(3) 0.012(3) 0.015(2) 0.022(3)
+C24 0.051(3) 0.061(4) 0.034(3) -0.002(3) 0.006(3) 0.038(3)
+C25 0.145(8) 0.082(5) 0.039(4) 0.023(4) 0.042(5) 0.090(6)
+C26 0.068(5) 0.096(6) 0.055(4) 0.020(4) 0.007(4) 0.053(5)
+C27 0.105(7) 0.115(7) 0.120(8) -0.033(6) -0.051(6) 0.106(7)
+C28 0.082(6) 0.105(6) 0.049(4) 0.052(4) -0.036(4) -0.012(5)
+C29 0.074(7) 0.62(4) 0.114(10) 0.252(18) 0.001(7) 0.029(14)
+C30 0.149(9) 0.141(9) 0.054(5) 0.065(5) 0.057(6) 0.113(8)
+C31 0.110(7) 0.062(5) 0.082(6) 0.050(4) 0.030(5) 0.021(5)
+C32 0.094(6) 0.046(4) 0.061(4) 0.021(3) 0.040(4) 0.021(4)
+C33 0.056(4) 0.048(4) 0.046(4) 0.013(3) 0.018(3) -0.007(3)
+C34 0.014(2) 0.035(2) 0.014(2) 0.0059(18) -0.0019(17) 0.0096(18)
+C35 0.025(2) 0.032(2) 0.021(2) 0.0050(19) -0.0033(19) 0.010(2)
+C36 0.0082(18) 0.030(2) 0.0130(19) 0.0013(17) -0.0030(15) 0.0125(17)
+C37 0.017(2) 0.032(2) 0.013(2) -0.0004(17) -0.0039(16) 0.0181(19)
+C38 0.024(2) 0.029(2) 0.016(2) -0.0031(18) -0.0035(18) 0.017(2)
+N1 0.0187(18) 0.032(2) 0.0087(16) -0.0003(14) -0.0050(14) 0.0193(16)
+N2 0.0109(16) 0.033(2) 0.0095(16) 0.0031(14) -0.0003(13) 0.0141(15)
+N3 0.0216(18) 0.030(2) 0.0120(17) -0.0001(15) -0.0016(14) 0.0163(16)
+N4 0.029(2) 0.029(2) 0.0150(18) 0.0034(16) -0.0032(16) 0.0089(17)
+N5 0.033(2) 0.032(2) 0.021(2) 0.0036(17) -0.0041(17) 0.0140(18)
+O1 0.0235(17) 0.0363(18) 0.0205(16) 0.0026(14) 0.0003(13) 0.0105(14)
+O2 0.054(2) 0.060(2) 0.031(2) 0.0152(18) 0.0199(18) 0.040(2)
+O3 0.137(5) 0.064(3) 0.083(4) 0.044(3) 0.084(4) 0.073(4)
+O4 0.0309(19) 0.049(2) 0.043(2) 0.0191(18) -0.0025(16) 0.0215(17)
+O5 0.045(3) 0.155(6) 0.048(3) 0.062(3) 0.024(2) 0.031(3)
+O6 0.093(4) 0.048(3) 0.058(3) 0.026(2) -0.016(3) 0.012(3)
+O7 0.0255(17) 0.045(2) 0.0179(16) 0.0091(14) 0.0051(14) 0.0090(15)
+C101 0.033(3) 0.030(3) 0.021(2) 0.0047(19) 0.011(2) 0.014(2)
+C102 0.082(5) 0.053(4) 0.047(4) 0.000(3) -0.010(4) 0.039(4)
+C103 0.041(3) 0.035(3) 0.021(2) 0.008(2) -0.002(2) 0.017(2)
+C104 0.073(5) 0.069(5) 0.048(4) 0.042(4) -0.023(4) -0.012(4)
+C105 0.055(4) 0.045(3) 0.055(4) 0.018(3) 0.001(3) 0.028(3)
+C106 0.057(4) 0.060(4) 0.070(5) 0.018(4) 0.001(4) 0.026(4)
+C107 0.041(4) 0.113(7) 0.059(5) 0.035(4) 0.016(3) 0.028(4)
+C108 0.057(4) 0.081(5) 0.061(5) 0.019(4) 0.011(4) 0.003(4)
+O101 0.033(2) 0.038(2) 0.060(3) 0.0192(19) 0.0048(19) 0.0098(17)
+O102 0.041(2) 0.038(2) 0.053(2) 0.0099(18) -0.0001(19) 0.0125(18)
+O103 0.038(2) 0.043(2) 0.0269(18) 0.0176(16) 0.0086(15) 0.0154(17)
+O104 0.043(2) 0.055(2) 0.045(2) 0.023(2) -0.0085(19) 0.0130(19)
+F101 0.159(6) 0.220(8) 0.099(4) 0.007(5) 0.016(4) 0.166(7)
+F102 0.148(5) 0.067(3) 0.074(3) 0.030(2) -0.031(3) 0.045(3)
+F103 0.177(7) 0.030(2) 0.180(6) 0.007(3) -0.087(5) 0.030(3)
+F104 0.073(3) 0.084(3) 0.072(3) 0.054(2) -0.037(2) -0.028(2)
+F105 0.132(6) 0.291(12) 0.076(4) 0.035(6) 0.034(4) -0.108(8)
+F106 0.161(7) 0.104(5) 0.286(11) 0.146(7) -0.127(7) -0.041(5)
+N101 0.063(4) 0.050(3) 0.082(4) 0.025(3) -0.013(3) 0.018(3)
+N102 0.077(6) 0.35(2) 0.072(6) 0.079(9) 0.015(5) 0.027(9)
+
+_geom_special_details
+;
+All esds (except the esd in the dihedral angle between two l.s. planes)
+are estimated using the full covariance matrix. The cell esds are taken
+into account individually in the estimation of esds in distances, angles
+and torsion angles; correlations between esds in cell parameters are only
+used when they are defined by crystal symmetry. An approximate (isotropic)
+treatment of cell esds is used for estimating esds involving l.s. planes.
+;
+
+loop_
+_geom_bond_atom_site_label_1
+_geom_bond_atom_site_label_2
+_geom_bond_distance
+_geom_bond_site_symmetry_2
+_geom_bond_publ_flag
+C1 N1 1.334(6) . ?
+C1 C3 1.367(6) . ?
+C1 H1 0.9500 . ?
+C2 N1 1.353(6) . ?
+C2 C4 1.371(6) . ?
+C2 H2 0.9500 . ?
+C3 C5 1.394(6) . ?
+C3 H3 0.9500 . ?
+C4 C5 1.403(6) . ?
+C4 H4 0.9500 . ?
+C5 C6 1.490(6) . ?
+C6 C8 1.390(6) . ?
+C6 C7 1.397(6) . ?
+C7 C9 1.371(6) . ?
+C7 H7 0.9500 . ?
+C8 C10 1.375(6) . ?
+C8 H8 0.9500 . ?
+C9 N2 1.342(6) . ?
+C9 H9 0.9500 . ?
+C10 N2 1.352(6) . ?
+C10 H10 0.9500 . ?
+C11 N2 1.497(5) . ?
+C11 C12 1.517(6) . ?
+C11 H11A 0.9900 . ?
+C11 H11B 0.9900 . ?
+C12 C14 1.382(6) . ?
+C12 C13 1.396(6) . ?
+C13 C15 1.384(6) . ?
+C13 H13 0.9500 . ?
+C14 C16 1.395(6) . ?
+C14 H14 0.9500 . ?
+C15 C17 1.383(7) . ?
+C15 H15 0.9500 . ?
+C16 C17 1.400(6) . ?
+C16 N3 1.418(6) . ?
+C17 C18 1.515(6) . ?
+C18 N1 1.505(5) 2 ?
+C18 H18A 0.9900 . ?
+C18 H18B 0.9900 . ?
+C19 N3 1.356(5) . ?
+C19 C20 1.357(7) . ?
+C19 H19 0.9500 . ?
+C20 N5 1.366(6) . ?
+C20 C21 1.491(6) . ?
+C21 O1 1.435(6) . ?
+C21 H21A 0.9900 . ?
+C21 H21B 0.9900 . ?
+C22 O1 1.429(6) . ?
+C22 C23 1.484(8) . ?
+C22 H22A 0.9900 . ?
+C22 H22B 0.9900 . ?
+C23 O2 1.431(7) . ?
+C23 H23A 0.9900 . ?
+C23 H23B 0.9900 . ?
+C24 O2 1.420(7) . ?
+C24 C25 1.442(11) . ?
+C24 H24A 0.9900 . ?
+C24 H24B 0.9900 . ?
+C25 O3 1.416(11) . ?
+C25 H25A 0.9900 . ?
+C25 H25B 0.9900 . ?
+C26 C27 1.331(12) . ?
+C26 O3 1.481(9) . ?
+C26 H26A 0.9900 . ?
+C26 H26B 0.9900 . ?
+C27 O4 1.605(11) . ?
+C27 H27A 0.9900 . ?
+C27 H27B 0.9900 . ?
+C28 C29 1.252(12) . ?
+C28 O4 1.391(8) . ?
+C28 H28A 0.9900 . ?
+C28 H28B 0.9900 . ?
+C29 O5 1.361(11) . ?
+C29 H29A 0.9900 . ?
+C29 H29B 0.9900 . ?
+C30 O5 1.388(12) . ?
+C30 C31 1.407(13) . ?
+C30 H30A 0.9900 . ?
+C30 H30B 0.9900 . ?
+C31 O6 1.396(10) . ?
+C31 H31A 0.9900 . ?
+C31 H31B 0.9900 . ?
+C32 C33 1.449(9) . ?
+C32 O6 1.464(10) . ?
+C32 H32A 0.9900 . ?
+C32 H32B 0.9900 . ?
+C33 O7 1.453(7) . ?
+C33 H33A 0.9900 . ?
+C33 H33B 0.9900 . ?
+C34 O7 1.362(5) . ?
+C34 C35 1.377(7) . ?
+C34 C36 1.425(7) . ?
+C35 C38 1.404(7) 2 ?
+C35 H35 0.9500 . ?
+C36 C36 1.417(9) 2 ?
+C36 C37 1.417(6) . ?
+C37 C38 1.356(7) . ?
+C37 H37 0.9500 . ?
+C38 C35 1.404(7) 2 ?
+C38 H38 0.9500 . ?
+N1 C18 1.505(5) 2 ?
+N3 N4 1.370(5) . ?
+N4 N5 1.300(6) . ?
+C101 O101 1.227(6) . ?
+C101 O102 1.232(6) . ?
+C101 C102 1.518(9) . ?
+C102 F103 1.301(9) . ?
+C102 F102 1.318(8) . ?
+C102 F101 1.324(11) . ?
+C103 O104 1.224(6) . ?
+C103 O103 1.227(6) . ?
+C103 C104 1.512(9) . ?
+C104 F106 1.260(10) . ?
+C104 F104 1.290(7) . ?
+C104 F105 1.341(14) . ?
+C105 N101 1.139(9) . ?
+C105 C106 1.443(10) . ?
+C106 H10A 0.9800 . ?
+C106 H10B 0.9800 . ?
+C106 H10C 0.9800 . ?
+C107 N102 1.118(11) . ?
+C107 C108 1.360(11) . ?
+C108 H10D 0.9800 . ?
+C108 H10E 0.9800 . ?
+C108 H10F 0.9800 . ?
+
+loop_
+_geom_angle_atom_site_label_1
+_geom_angle_atom_site_label_2
+_geom_angle_atom_site_label_3
+_geom_angle
+_geom_angle_site_symmetry_1
+_geom_angle_site_symmetry_3
+_geom_angle_publ_flag
+N1 C1 C3 121.3(4) . . ?
+N1 C1 H1 119.3 . . ?
+C3 C1 H1 119.3 . . ?
+N1 C2 C4 120.4(4) . . ?
+N1 C2 H2 119.8 . . ?
+C4 C2 H2 119.8 . . ?
+C1 C3 C5 120.4(4) . . ?
+C1 C3 H3 119.8 . . ?
+C5 C3 H3 119.8 . . ?
+C2 C4 C5 120.4(4) . . ?
+C2 C4 H4 119.8 . . ?
+C5 C4 H4 119.8 . . ?
+C3 C5 C4 116.9(4) . . ?
+C3 C5 C6 121.8(4) . . ?
+C4 C5 C6 121.2(4) . . ?
+C8 C6 C7 117.6(4) . . ?
+C8 C6 C5 122.4(4) . . ?
+C7 C6 C5 119.9(4) . . ?
+C9 C7 C6 120.1(4) . . ?
+C9 C7 H7 120.0 . . ?
+C6 C7 H7 120.0 . . ?
+C10 C8 C6 120.4(4) . . ?
+C10 C8 H8 119.8 . . ?
+C6 C8 H8 119.8 . . ?
+N2 C9 C7 120.9(4) . . ?
+N2 C9 H9 119.5 . . ?
+C7 C9 H9 119.5 . . ?
+N2 C10 C8 120.3(4) . . ?
+N2 C10 H10 119.8 . . ?
+C8 C10 H10 119.8 . . ?
+N2 C11 C12 107.7(3) . . ?
+N2 C11 H11A 110.2 . . ?
+C12 C11 H11A 110.2 . . ?
+N2 C11 H11B 110.2 . . ?
+C12 C11 H11B 110.2 . . ?
+H11A C11 H11B 108.5 . . ?
+C14 C12 C13 119.9(4) . . ?
+C14 C12 C11 120.0(4) . . ?
+C13 C12 C11 120.0(4) . . ?
+C15 C13 C12 119.2(4) . . ?
+C15 C13 H13 120.4 . . ?
+C12 C13 H13 120.4 . . ?
+C12 C14 C16 119.7(4) . . ?
+C12 C14 H14 120.2 . . ?
+C16 C14 H14 120.2 . . ?
+C17 C15 C13 122.1(4) . . ?
+C17 C15 H15 118.9 . . ?
+C13 C15 H15 118.9 . . ?
+C14 C16 C17 121.1(4) . . ?
+C14 C16 N3 117.0(4) . . ?
+C17 C16 N3 121.8(4) . . ?
+C15 C17 C16 117.5(4) . . ?
+C15 C17 C18 119.0(4) . . ?
+C16 C17 C18 123.2(4) . . ?
+N1 C18 C17 109.0(3) 2 . ?
+N1 C18 H18A 109.9 2 . ?
+C17 C18 H18A 109.9 . . ?
+N1 C18 H18B 109.9 2 . ?
+C17 C18 H18B 109.9 . . ?
+H18A C18 H18B 108.3 . . ?
+N3 C19 C20 105.0(4) . . ?
+N3 C19 H19 127.5 . . ?
+C20 C19 H19 127.5 . . ?
+C19 C20 N5 108.7(4) . . ?
+C19 C20 C21 129.7(4) . . ?
+N5 C20 C21 121.6(5) . . ?
+O1 C21 C20 113.0(4) . . ?
+O1 C21 H21A 109.0 . . ?
+C20 C21 H21A 109.0 . . ?
+O1 C21 H21B 109.0 . . ?
+C20 C21 H21B 109.0 . . ?
+H21A C21 H21B 107.8 . . ?
+O1 C22 C23 109.1(4) . . ?
+O1 C22 H22A 109.9 . . ?
+C23 C22 H22A 109.9 . . ?
+O1 C22 H22B 109.9 . . ?
+C23 C22 H22B 109.9 . . ?
+H22A C22 H22B 108.3 . . ?
+O2 C23 C22 108.0(5) . . ?
+O2 C23 H23A 110.1 . . ?
+C22 C23 H23A 110.1 . . ?
+O2 C23 H23B 110.1 . . ?
+C22 C23 H23B 110.1 . . ?
+H23A C23 H23B 108.4 . . ?
+O2 C24 C25 110.9(6) . . ?
+O2 C24 H24A 109.5 . . ?
+C25 C24 H24A 109.5 . . ?
+O2 C24 H24B 109.5 . . ?
+C25 C24 H24B 109.5 . . ?
+H24A C24 H24B 108.0 . . ?
+O3 C25 C24 112.1(6) . . ?
+O3 C25 H25A 109.2 . . ?
+C24 C25 H25A 109.2 . . ?
+O3 C25 H25B 109.2 . . ?
+C24 C25 H25B 109.2 . . ?
+H25A C25 H25B 107.9 . . ?
+C27 C26 O3 98.8(7) . . ?
+C27 C26 H26A 112.0 . . ?
+O3 C26 H26A 112.0 . . ?
+C27 C26 H26B 112.0 . . ?
+O3 C26 H26B 112.0 . . ?
+H26A C26 H26B 109.7 . . ?
+C26 C27 O4 114.9(7) . . ?
+C26 C27 H27A 108.5 . . ?
+O4 C27 H27A 108.5 . . ?
+C26 C27 H27B 108.5 . . ?
+O4 C27 H27B 108.5 . . ?
+H27A C27 H27B 107.5 . . ?
+C29 C28 O4 124.1(6) . . ?
+C29 C28 H28A 106.3 . . ?
+O4 C28 H28A 106.3 . . ?
+C29 C28 H28B 106.3 . . ?
+O4 C28 H28B 106.3 . . ?
+H28A C28 H28B 106.4 . . ?
+C28 C29 O5 128.7(9) . . ?
+C28 C29 H29A 105.1 . . ?
+O5 C29 H29A 105.1 . . ?
+C28 C29 H29B 105.1 . . ?
+O5 C29 H29B 105.1 . . ?
+H29A C29 H29B 105.9 . . ?
+O5 C30 C31 110.9(6) . . ?
+O5 C30 H30A 109.5 . . ?
+C31 C30 H30A 109.5 . . ?
+O5 C30 H30B 109.5 . . ?
+C31 C30 H30B 109.5 . . ?
+H30A C30 H30B 108.1 . . ?
+O6 C31 C30 111.7(8) . . ?
+O6 C31 H31A 109.3 . . ?
+C30 C31 H31A 109.3 . . ?
+O6 C31 H31B 109.3 . . ?
+C30 C31 H31B 109.3 . . ?
+H31A C31 H31B 107.9 . . ?
+C33 C32 O6 108.1(6) . . ?
+C33 C32 H32A 110.1 . . ?
+O6 C32 H32A 110.1 . . ?
+C33 C32 H32B 110.1 . . ?
+O6 C32 H32B 110.1 . . ?
+H32A C32 H32B 108.4 . . ?
+C32 C33 O7 111.8(5) . . ?
+C32 C33 H33A 109.3 . . ?
+O7 C33 H33A 109.3 . . ?
+C32 C33 H33B 109.3 . . ?
+O7 C33 H33B 109.3 . . ?
+H33A C33 H33B 107.9 . . ?
+O7 C34 C35 124.0(4) . . ?
+O7 C34 C36 115.2(4) . . ?
+C35 C34 C36 120.8(4) . . ?
+C34 C35 C38 119.3(5) . 2 ?
+C34 C35 H35 120.4 . . ?
+C38 C35 H35 120.4 2 . ?
+C36 C36 C37 119.6(5) 2 . ?
+C36 C36 C34 118.4(5) 2 . ?
+C37 C36 C34 121.9(4) . . ?
+C38 C37 C36 119.9(4) . . ?
+C38 C37 H37 120.1 . . ?
+C36 C37 H37 120.1 . . ?
+C37 C38 C35 122.0(4) . 2 ?
+C37 C38 H38 119.0 . . ?
+C35 C38 H38 119.0 2 . ?
+C1 N1 C2 120.4(4) . . ?
+C1 N1 C18 120.5(4) . 2 ?
+C2 N1 C18 119.1(4) . 2 ?
+C9 N2 C10 120.6(4) . . ?
+C9 N2 C11 119.3(4) . . ?
+C10 N2 C11 119.9(4) . . ?
+C19 N3 N4 110.0(4) . . ?
+C19 N3 C16 130.4(4) . . ?
+N4 N3 C16 119.3(3) . . ?
+N5 N4 N3 107.0(3) . . ?
+N4 N5 C20 109.4(4) . . ?
+C22 O1 C21 112.0(4) . . ?
+C24 O2 C23 111.2(5) . . ?
+C25 O3 C26 101.1(6) . . ?
+C28 O4 C27 123.6(7) . . ?
+C29 O5 C30 109.4(11) . . ?
+C31 O6 C32 107.8(7) . . ?
+C34 O7 C33 116.5(4) . . ?
+O101 C101 O102 129.2(5) . . ?
+O101 C101 C102 113.1(5) . . ?
+O102 C101 C102 117.7(5) . . ?
+F103 C102 F102 108.6(7) . . ?
+F103 C102 F101 104.9(7) . . ?
+F102 C102 F101 105.0(7) . . ?
+F103 C102 C101 114.3(6) . . ?
+F102 C102 C101 112.4(5) . . ?
+F101 C102 C101 111.0(7) . . ?
+O104 C103 O103 130.2(5) . . ?
+O104 C103 C104 115.4(5) . . ?
+O103 C103 C104 114.3(5) . . ?
+F106 C104 F104 107.4(7) . . ?
+F106 C104 F105 99.1(9) . . ?
+F104 C104 F105 105.1(9) . . ?
+F106 C104 C103 115.6(8) . . ?
+F104 C104 C103 117.1(5) . . ?
+F105 C104 C103 110.5(7) . . ?
+N101 C105 C106 179.3(9) . . ?
+C105 C106 H10A 109.5 . . ?
+C105 C106 H10B 109.5 . . ?
+H10A C106 H10B 109.5 . . ?
+C105 C106 H10C 109.5 . . ?
+H10A C106 H10C 109.5 . . ?
+H10B C106 H10C 109.5 . . ?
+N102 C107 C108 179.3(14) . . ?
+C107 C108 H10D 109.5 . . ?
+C107 C108 H10E 109.5 . . ?
+H10D C108 H10E 109.5 . . ?
+C107 C108 H10F 109.5 . . ?
+H10D C108 H10F 109.5 . . ?
+H10E C108 H10F 109.5 . . ?
+
+loop_
+_geom_torsion_atom_site_label_1
+_geom_torsion_atom_site_label_2
+_geom_torsion_atom_site_label_3
+_geom_torsion_atom_site_label_4
+_geom_torsion
+_geom_torsion_site_symmetry_1
+_geom_torsion_site_symmetry_2
+_geom_torsion_site_symmetry_3
+_geom_torsion_site_symmetry_4
+_geom_torsion_publ_flag
+N1 C1 C3 C5 0.3(6) . . . . ?
+N1 C2 C4 C5 1.1(6) . . . . ?
+C1 C3 C5 C4 3.1(6) . . . . ?
+C1 C3 C5 C6 -174.6(4) . . . . ?
+C2 C4 C5 C3 -3.8(5) . . . . ?
+C2 C4 C5 C6 173.9(3) . . . . ?
+C3 C5 C6 C8 -168.8(4) . . . . ?
+C4 C5 C6 C8 13.6(5) . . . . ?
+C3 C5 C6 C7 14.7(5) . . . . ?
+C4 C5 C6 C7 -162.9(4) . . . . ?
+C8 C6 C7 C9 -0.6(5) . . . . ?
+C5 C6 C7 C9 176.0(3) . . . . ?
+C7 C6 C8 C10 1.4(5) . . . . ?
+C5 C6 C8 C10 -175.2(3) . . . . ?
+C6 C7 C9 N2 -0.7(6) . . . . ?
+C6 C8 C10 N2 -0.8(6) . . . . ?
+N2 C11 C12 C14 88.4(5) . . . . ?
+N2 C11 C12 C13 -87.7(5) . . . . ?
+C14 C12 C13 C15 -5.7(6) . . . . ?
+C11 C12 C13 C15 170.4(4) . . . . ?
+C13 C12 C14 C16 4.9(6) . . . . ?
+C11 C12 C14 C16 -171.2(4) . . . . ?
+C12 C13 C15 C17 0.2(6) . . . . ?
+C12 C14 C16 C17 1.4(6) . . . . ?
+C12 C14 C16 N3 179.1(3) . . . . ?
+C13 C15 C17 C16 5.9(6) . . . . ?
+C13 C15 C17 C18 -167.5(4) . . . . ?
+C14 C16 C17 C15 -6.7(6) . . . . ?
+N3 C16 C17 C15 175.7(4) . . . . ?
+C14 C16 C17 C18 166.4(4) . . . . ?
+N3 C16 C17 C18 -11.2(6) . . . . ?
+C15 C17 C18 N1 83.8(5) . . . 2 ?
+C16 C17 C18 N1 -89.3(5) . . . 2 ?
+N3 C19 C20 N5 0.2(5) . . . . ?
+N3 C19 C20 C21 -179.5(5) . . . . ?
+C19 C20 C21 O1 78.8(7) . . . . ?
+N5 C20 C21 O1 -100.9(6) . . . . ?
+O1 C22 C23 O2 66.1(5) . . . . ?
+O2 C24 C25 O3 65.4(6) . . . . ?
+O3 C26 C27 O4 -86.2(9) . . . . ?
+O4 C28 C29 O5 -7(4) . . . . ?
+O5 C30 C31 O6 69.5(9) . . . . ?
+O6 C32 C33 O7 -71.5(8) . . . . ?
+O7 C34 C35 C38 -177.1(4) . . . 2 ?
+C36 C34 C35 C38 1.4(6) . . . 2 ?
+O7 C34 C36 C36 177.6(4) . . . 2 ?
+C35 C34 C36 C36 -1.1(7) . . . 2 ?
+O7 C34 C36 C37 -2.5(6) . . . . ?
+C35 C34 C36 C37 178.9(4) . . . . ?
+C36 C36 C37 C38 -0.8(7) 2 . . . ?
+C34 C36 C37 C38 179.2(4) . . . . ?
+C36 C37 C38 C35 0.5(6) . . . 2 ?
+C3 C1 N1 C2 -3.1(6) . . . . ?
+C3 C1 N1 C18 175.3(4) . . . 2 ?
+C4 C2 N1 C1 2.4(6) . . . . ?
+C4 C2 N1 C18 -176.0(3) . . . 2 ?
+C7 C9 N2 C10 1.4(6) . . . . ?
+C7 C9 N2 C11 -173.8(3) . . . . ?
+C8 C10 N2 C9 -0.6(6) . . . . ?
+C8 C10 N2 C11 174.5(3) . . . . ?
+C12 C11 N2 C9 85.7(4) . . . . ?
+C12 C11 N2 C10 -89.6(4) . . . . ?
+C20 C19 N3 N4 -0.2(5) . . . . ?
+C20 C19 N3 C16 -174.0(4) . . . . ?
+C14 C16 N3 C19 129.4(5) . . . . ?
+C17 C16 N3 C19 -52.9(6) . . . . ?
+C14 C16 N3 N4 -43.9(5) . . . . ?
+C17 C16 N3 N4 133.8(4) . . . . ?
+C19 N3 N4 N5 0.2(5) . . . . ?
+C16 N3 N4 N5 174.8(4) . . . . ?
+N3 N4 N5 C20 -0.1(5) . . . . ?
+C19 C20 N5 N4 -0.1(6) . . . . ?
+C21 C20 N5 N4 179.7(4) . . . . ?
+C23 C22 O1 C21 -171.9(4) . . . . ?
+C20 C21 O1 C22 63.3(6) . . . . ?
+C25 C24 O2 C23 170.3(5) . . . . ?
+C22 C23 O2 C24 164.7(4) . . . . ?
+C24 C25 O3 C26 170.9(5) . . . . ?
+C27 C26 O3 C25 177.5(7) . . . . ?
+C29 C28 O4 C27 -129(2) . . . . ?
+C26 C27 O4 C28 -85.6(11) . . . . ?
+C28 C29 O5 C30 136(3) . . . . ?
+C31 C30 O5 C29 177.4(11) . . . . ?
+C30 C31 O6 C32 178.6(7) . . . . ?
+C33 C32 O6 C31 -173.5(6) . . . . ?
+C35 C34 O7 C33 2.2(7) . . . . ?
+C36 C34 O7 C33 -176.4(5) . . . . ?
+C32 C33 O7 C34 169.3(6) . . . . ?
+O101 C101 C102 F103 -174.2(7) . . . . ?
+O102 C101 C102 F103 6.5(10) . . . . ?
+O101 C101 C102 F102 -49.8(9) . . . . ?
+O102 C101 C102 F102 130.9(7) . . . . ?
+O101 C101 C102 F101 67.5(7) . . . . ?
+O102 C101 C102 F101 -111.9(7) . . . . ?
+O104 C103 C104 F106 -34.8(12) . . . . ?
+O103 C103 C104 F106 149.3(9) . . . . ?
+O104 C103 C104 F104 -163.1(8) . . . . ?
+O103 C103 C104 F104 21.0(11) . . . . ?
+O104 C103 C104 F105 76.7(10) . . . . ?
+O103 C103 C104 F105 -99.2(8) . . . . ?
+
+_diffrn_measured_fraction_theta_max 0.961
+_diffrn_reflns_theta_full 64.94
+_diffrn_measured_fraction_theta_full 0.961
+_refine_diff_density_max 1.693
+_refine_diff_density_min -0.992
+_refine_diff_density_rms 0.109
+
+# start Validation Reply Form
+_vrf_PLAT213_I
+;
+PROBLEM: Atom C5 has ADP max/min Ratio ..... 5.1 oblat
+RESPONSE: The atoms of the glycol chain and of the CBPQT4+ ring showed elongated
+displacement parameters. Attempts to model this disorder did not significantly
+improve the refinement.
+;
+_vrf_PLAT222_I
+;
+PROBLEM: Large Non-Solvent H Uiso(max)/Uiso(min) .. 10.0 Ratio
+RESPONSE: Hydrogen atoms were refined as riding models with their isotropic
+displacement parameters linked to their parent atoms.
+In this case the parent atom exhibits disorder with an elongated
+displacement parameter and therefore the riding hydrogen atom is also large.
+;
+_vrf_PLAT241_I
+;
+PROBLEM: Check High Ueq as Compared to Neighbors for C27
+RESPONSE: C27 and C29 are part of the disordered glycol chain, however they
+are bonded to C26 and O5 which are relatively well-ordered parts of the
+structure.
+;
+
+# end Validation Reply Form
+
+
+
diff --git a/src/mol-io/reader/cif.ts b/src/mol-io/reader/cif.ts
index f45c707fe645f62f0e7c4a0e5949cb71a961092e..436e3137c4e258f1ead1438cc41690af5168784d 100644
--- a/src/mol-io/reader/cif.ts
+++ b/src/mol-io/reader/cif.ts
@@ -14,6 +14,7 @@ import { CCD_Schema, CCD_Database } from './cif/schema/ccd'
import { BIRD_Schema, BIRD_Database } from './cif/schema/bird'
import { dic_Schema, dic_Database } from './cif/schema/dic'
import { DensityServer_Data_Schema, DensityServer_Data_Database } from './cif/schema/density-server'
+import { cifCore_Database, cifCore_Schema, cifCore_Aliases } from './cif/schema/cif-core'
export const CIF = {
parse: (data: string|Uint8Array) => typeof data === 'string' ? parseText(data) : parseBinary(data),
@@ -26,7 +27,8 @@ export const CIF = {
CCD: (frame: CifFrame) => toDatabase<CCD_Schema, CCD_Database>(CCD_Schema, frame),
BIRD: (frame: CifFrame) => toDatabase<BIRD_Schema, BIRD_Database>(BIRD_Schema, frame),
dic: (frame: CifFrame) => toDatabase<dic_Schema, dic_Database>(dic_Schema, frame),
- densityServer: (frame: CifFrame) => toDatabase<DensityServer_Data_Schema, DensityServer_Data_Database>(DensityServer_Data_Schema, frame)
+ cifCore: (frame: CifFrame) => toDatabase<cifCore_Schema, cifCore_Database>(cifCore_Schema, frame, cifCore_Aliases),
+ densityServer: (frame: CifFrame) => toDatabase<DensityServer_Data_Schema, DensityServer_Data_Database>(DensityServer_Data_Schema, frame),
}
}
diff --git a/src/mol-io/reader/cif/data-model.ts b/src/mol-io/reader/cif/data-model.ts
index 516e022ce0b132acbd30b98fbc349c329e1c21cf..b4e1b4b93699d4f621b4858d2e9641482b520ab1 100644
--- a/src/mol-io/reader/cif/data-model.ts
+++ b/src/mol-io/reader/cif/data-model.ts
@@ -1,5 +1,5 @@
/**
- * Copyright (c) 2017-2018 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2017-2019 mol* contributors, licensed under MIT, See LICENSE file for more info.
*
* @author David Sehnal <david.sehnal@gmail.com>
* @author Alexander Rose <alexander.rose@weirdbyte.de>
@@ -23,23 +23,31 @@ export function CifFile(blocks: ArrayLike<CifBlock>, name?: string): CifFile {
export interface CifFrame {
readonly header: string,
- // Category names stored separately so that the ordering can be preserved.
+ /** Category names, stored separately so that the ordering can be preserved. */
readonly categoryNames: ReadonlyArray<string>,
readonly categories: CifCategories
}
export interface CifBlock extends CifFrame {
readonly saveFrames: CifFrame[]
+ getField(name: string): CifField | undefined
}
export function CifBlock(categoryNames: string[], categories: CifCategories, header: string, saveFrames: CifFrame[] = []): CifBlock {
- return { categoryNames, header, categories, saveFrames };
+ return {
+ categoryNames, header, categories, saveFrames,
+ getField(name: string) {
+ const [ category, field ] = name.split('.')
+ return categories[category].getField(field || '')
+ }
+ };
}
-export function CifSafeFrame(categoryNames: string[], categories: CifCategories, header: string): CifFrame {
+export function CifSaveFrame(categoryNames: string[], categories: CifCategories, header: string): CifFrame {
return { categoryNames, header, categories };
}
+export type CifAliases = { readonly [name: string]: string[] }
export type CifCategories = { readonly [name: string]: CifCategory }
export interface CifCategory {
diff --git a/src/mol-io/reader/cif/schema.ts b/src/mol-io/reader/cif/schema.ts
index c84d74e637a4152dbd65592a18dc3c5a7ffa33fb..f465a8fd29828e99fe396cdaea1756325592afc8 100644
--- a/src/mol-io/reader/cif/schema.ts
+++ b/src/mol-io/reader/cif/schema.ts
@@ -1,5 +1,5 @@
/**
- * Copyright (c) 2017-2018 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2017-2019 mol* contributors, licensed under MIT, See LICENSE file for more info.
*
* @author David Sehnal <david.sehnal@gmail.com>
* @author Alexander Rose <alexander.rose@weirdbyte.de>
@@ -10,16 +10,31 @@ import { Tensor } from '../../../mol-math/linear-algebra'
import { arrayEqual } from '../../../mol-util'
import * as Data from './data-model'
-export function toDatabaseCollection<Schema extends Database.Schema>(schema: Schema, file: Data.CifFile): DatabaseCollection<Schema> {
+export namespace FieldPath {
+ export function canonical(path: string) {
+ return path.replace('.', '_').replace(/\[/, '_').replace(/(\[|\])/g, '')
+ }
+
+ export function equal(pathA: string, pathB: string) {
+ return canonical(pathA) === canonical(pathB)
+ }
+
+ export function create(category: string, field: string, asCanonical = false) {
+ const p = `${category}${field ? `.${field}` : ''}`
+ return asCanonical ? canonical(p) : p
+ }
+}
+
+export function toDatabaseCollection<Schema extends Database.Schema>(schema: Schema, file: Data.CifFile, aliases?: Data.CifAliases): DatabaseCollection<Schema> {
const dbc: DatabaseCollection<Schema> = {}
for (const data of file.blocks) {
- dbc[data.header] = toDatabase(schema, data)
+ dbc[data.header] = toDatabase(schema, data, aliases)
}
return dbc;
}
-export function toDatabase<Schema extends Database.Schema, Frame extends Database<Schema> = Database<Schema>>(schema: Schema, frame: Data.CifFrame): Frame {
- return createDatabase(schema, frame) as Frame;
+export function toDatabase<Schema extends Database.Schema, Frame extends Database<Schema> = Database<Schema>>(schema: Schema, frame: Data.CifFrame, aliases?: Data.CifAliases): Frame {
+ return createDatabase(schema, frame, aliases) as Frame;
}
export function toTable<Schema extends Table.Schema, R extends Table<Schema> = Table<Schema>>(schema: Schema, category: Data.CifCategory): R {
@@ -51,7 +66,7 @@ function createColumn<T>(schema: Column.Schema, field: Data.CifField, value: (ro
};
}
-function createListColumn<T extends number|string>(schema: Column.Schema.List<T>, category: Data.CifCategory, key: string): Column<(number|string)[]> {
+function createListColumn<T extends number | string>(schema: Column.Schema.List<T>, category: Data.CifCategory, key: string): Column<(number | string)[]> {
const separator = schema.separator;
const itemParse = schema.itemParse;
@@ -134,15 +149,62 @@ class CategoryTable implements Table<any> { // tslint:disable-line:class-name
}
}
-function createDatabase(schema: Database.Schema, frame: Data.CifFrame): Database<any> {
+function createDatabase(schema: Database.Schema, frame: Data.CifFrame, aliases?: Data.CifAliases): Database<any> {
const tables = Object.create(null);
for (const k of Object.keys(schema)) {
- tables[k] = createTable(k, (schema as any)[k], frame);
+ tables[k] = createTable(k, schema[k], frame, aliases);
}
return Database.ofTables(frame.header, schema, tables);
}
-function createTable(key: string, schema: Table.Schema, frame: Data.CifFrame) {
- const cat = frame.categories[key];
+type FlatFrame = { [k: string]: Data.CifField }
+
+function flattenFrame(frame: Data.CifFrame): FlatFrame {
+ const flatFrame = Object.create(null)
+ for (const c of Object.keys(frame.categories)) {
+ for (const f of frame.categories[c].fieldNames) {
+ const p = FieldPath.create(c, f, true)
+ flatFrame[p] = frame.categories[c].getField(f)
+ }
+ }
+ return flatFrame
+}
+
+function getField(field: string, category: string, flatFrame: FlatFrame, aliases?: Data.CifAliases) {
+ const path = FieldPath.create(category, field)
+ const canonicalPath = FieldPath.canonical(path)
+ if (canonicalPath in flatFrame) return flatFrame[canonicalPath]
+ if (aliases && path in aliases) {
+ for (const aliased of aliases[path]) {
+ const canonicalAliased = FieldPath.canonical(aliased)
+ if (canonicalAliased in flatFrame) return flatFrame[canonicalAliased]
+ }
+ }
+}
+
+function createTable(key: string, schema: Table.Schema, frame: Data.CifFrame, aliases?: Data.CifAliases) {
+ let cat = frame.categories[key];
+ if (aliases) {
+ const flatFrame = flattenFrame(frame)
+ const fields: { [k: string]: Data.CifField } = Object.create(null)
+ const fieldNames: string[] = []
+ let rowCount = 0
+ for (const k of Object.keys(schema)) {
+ const field = getField(k, key, flatFrame, aliases)
+ if (field) {
+ fields[k] = field
+ fieldNames.push(k)
+ rowCount = field.rowCount
+ }
+ }
+ cat = {
+ rowCount,
+ name: key,
+ fieldNames: [...fieldNames],
+ getField(name: string) {
+ return fields[name];
+ }
+ }
+ }
return new CategoryTable(cat || Data.CifCategory.empty(key), schema, !!cat);
}
\ No newline at end of file
diff --git a/src/mol-io/reader/cif/schema/cif-core.ts b/src/mol-io/reader/cif/schema/cif-core.ts
new file mode 100644
index 0000000000000000000000000000000000000000..ddde84aaa47f344030ebe90a6d3750ab80acd1ef
--- /dev/null
+++ b/src/mol-io/reader/cif/schema/cif-core.ts
@@ -0,0 +1,637 @@
+/**
+ * Copyright (c) 2017-2019 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ *
+ * Code-generated 'cifCore' schema file. Dictionary versions: CifCore 3.0.11.
+ *
+ * @author molstar/ciftools package
+ */
+
+import { Database, Column } from '../../../../mol-data/db'
+
+import Schema = Column.Schema
+
+const int = Schema.int;
+const float = Schema.float;
+const str = Schema.str;
+
+export const cifCore_Schema = {
+ /**
+ * The CATEGORY of data items used to describe the parameters of
+ * the crystal unit cell and their measurement.
+ */
+ cell: {
+ /**
+ * The number of the formula units in the unit cell as specified
+ * by _chemical_formula.structural, _chemical_formula.moiety or
+ * _chemical_formula.sum.
+ */
+ formula_units_Z: int,
+ /**
+ * Volume of the crystal unit cell.
+ */
+ volume: float,
+ /**
+ * The angle between the bounding cell axes.
+ */
+ angle_alpha: float,
+ /**
+ * The angle between the bounding cell axes.
+ */
+ angle_beta: float,
+ /**
+ * The angle between the bounding cell axes.
+ */
+ angle_gamma: float,
+ /**
+ * The length of each cell axis.
+ */
+ length_a: float,
+ /**
+ * The length of each cell axis.
+ */
+ length_b: float,
+ /**
+ * The length of each cell axis.
+ */
+ length_c: float,
+ },
+ /**
+ * The CATEGORY of data items which describe the composition and
+ * chemical properties of the compound under study. The formula data
+ * items must be consistent with the density, unit-cell and Z values.
+ */
+ chemical: {
+ /**
+ * The temperature at which a crystalline solid changes to a liquid.
+ */
+ melting_point: float,
+ /**
+ * Trivial name by which the compound is commonly known.
+ */
+ name_common: str,
+ /**
+ * IUPAC or Chemical Abstracts full name of compound.
+ */
+ name_systematic: str,
+ },
+ /**
+ * The CATEGORY of data items which specify the composition and chemical
+ * properties of the compound. The formula data items must agree
+ * with those that specify the density, unit-cell and Z values.
+ *
+ * The following rules apply to the construction of the data items
+ * _chemical_formula.analytical, *.structural and *.sum. For the
+ * data item *.moiety the formula construction is broken up into
+ * residues or moieties, i.e. groups of atoms that form a molecular
+ * unit or molecular ion. The rules given below apply within each
+ * moiety but different requirements apply to the way that moieties
+ * are connected (see _chemical_formula.moiety).
+ *
+ * 1. Only recognized element symbols may be used.
+ *
+ * 2. Each element symbol is followed by a 'count' number. A count of
+ * '1' may be omitted.
+ *
+ * 3. A space or parenthesis must separate each cluster of (element
+ * symbol + count).
+ *
+ * 4. Where a group of elements is enclosed in parentheses, the
+ * multiplier for the group must follow the closing parentheses.
+ * That is, all element and group multipliers are assumed to be
+ * printed as subscripted numbers. [An exception to this rule
+ * exists for *.moiety formulae where pre- and post-multipliers
+ * are permitted for molecular units].
+ *
+ * 5. Unless the elements are ordered in a manner that corresponds to
+ * their chemical structure, as in _chemical_formula.structural,
+ * the order of the elements within any group or moiety
+ * depends on whether or not carbon is present. If carbon is
+ * present, the order should be: C, then H, then the other
+ * elements in alphabetical order of their symbol. If carbon is
+ * not present, the elements are listed purely in alphabetic order
+ * of their symbol. This is the 'Hill' system used by Chemical
+ * Abstracts. This ordering is used in _chemical_formula.moiety
+ * and _chemical_formula.sum.
+ *
+ * _chemical_formula.iupac '[Mo (C O)4 (C18 H33 P)2]'
+ * _chemical_formula.moiety 'C40 H66 Mo O4 P2'
+ * _chemical_formula.structural '((C O)4 (P (C6 H11)3)2)Mo'
+ * _chemical_formula.sum 'C40 H66 Mo O4 P2'
+ * _chemical_formula.weight 768.81
+ */
+ chemical_formula: {
+ /**
+ * Formula with each discrete bonded residue or ion shown as a
+ * separate moiety. See above CHEMICAL_FORMULA for rules
+ * for writing chemical formulae. In addition to the general
+ * formulae requirements, the following rules apply:
+ * 1. Moieties are separated by commas ','.
+ * 2. The order of elements within a moiety follows general rule
+ * 5 in CHEMICAL_FORMULA.
+ * 3. Parentheses are not used within moieties but may surround
+ * a moiety. Parentheses may not be nested.
+ * 4. Charges should be placed at the end of the moiety. The
+ * Singlege '+' or '-' may be preceded by a numerical multiplier
+ * and should be separated from the last (element symbol +
+ * count) by a space. Pre- or post-multipliers may be used for
+ * individual moieties.
+ */
+ moiety: str,
+ /**
+ * Chemical formulae in which all discrete bonded residues and ions are
+ * summed over the constituent elements, following the ordering given
+ * in rule 5 of the CATEGORY description. Parentheses normally not used.
+ */
+ sum: str,
+ /**
+ * Mass corresponding to the formulae _chemical_formula.structural,
+ * *_iupac, *_moiety or *_sum and, together with the Z value and cell
+ * parameters yield the density given as _exptl_crystal.density_diffrn.
+ */
+ weight: float,
+ },
+ /**
+ * The CATEGORY of data items used to specify space group
+ * information about the crystal used in the diffraction measurements.
+ *
+ * Space-group types are identified by their number as listed in
+ * International Tables for Crystallography Volume A, or by their
+ * Schoenflies symbol. Specific settings of the space groups can
+ * be identified by their Hall symbol, by specifying their
+ * symmetry operations or generators, or by giving the
+ * transformation that relates the specific setting to the
+ * reference setting based on International Tables Volume A and
+ * stored in this dictionary.
+ *
+ * The commonly used Hermann-Mauguin symbol determines the
+ * space-group type uniquely but several different Hermann-Mauguin
+ * symbols may refer to the same space-group type. A
+ * Hermann-Mauguin symbol contains information on the choice of
+ * the basis, but not on the choice of origin.
+ *
+ * Ref: International Tables for Crystallography (2002). Volume A,
+ * Space-group symmetry, edited by Th. Hahn, 5th ed.
+ * Dordrecht: Kluwer Academic Publishers.
+ */
+ space_group: {
+ /**
+ * The name of the system of geometric crystal classes of space
+ * groups (crystal system) to which the space group belongs.
+ * Note that rhombohedral space groups belong to the
+ * trigonal system.
+ */
+ crystal_system: str,
+ /**
+ * The full international Hermann-Mauguin space-group symbol as
+ * defined in Section 2.2.3 and given as the second item of the
+ * second line of each of the space-group tables of Part 7 of
+ * International Tables for Crystallography Volume A (2002).
+ *
+ * Each component of the space-group name is separated by a
+ * space or an underscore character. The use of a space is
+ * strongly recommended. The underscore is only retained
+ * because it was used in old CIFs. It should not be used in
+ * new CIFs.
+ *
+ * Subscripts should appear without special symbols. Bars should
+ * be given as negative signs before the numbers to which they
+ * apply. The commonly used Hermann-Mauguin symbol determines the
+ * space-group type uniquely but a given space-group type may
+ * be described by more than one Hermann-Mauguin symbol. The
+ * space-group type is best described using
+ * _space_group.IT_number or _space_group.name_Schoenflies. The
+ * full international Hermann-Mauguin symbol contains information
+ * about the choice of basis for monoclinic and orthorhombic
+ * space groups but does not give information about the choice
+ * of origin. To define the setting uniquely use
+ * _space_group.name_Hall, or list the symmetry operations
+ * or generators.
+ *
+ * Ref: International Tables for Crystallography (2002). Volume A,
+ * Space-group symmetry, edited by Th. Hahn, 5th ed.
+ * Dordrecht: Kluwer Academic Publishers.
+ */
+ 'name_H-M_full': str,
+ },
+ /**
+ * The CATEGORY of data items used to describe symmetry equivalent sites
+ * in the crystal unit cell.
+ */
+ space_group_symop: {
+ /**
+ * A parsable string giving one of the symmetry operations of the
+ * space group in algebraic form. If W is a matrix representation
+ * of the rotational part of the symmetry operation defined by the
+ * positions and signs of x, y and z, and w is a column of
+ * translations defined by fractions, an equivalent position
+ * X' is generated from a given position X by the equation
+ *
+ * X' = WX + w
+ *
+ * (Note: X is used to represent bold_italics_x in International
+ * Tables for Crystallography Vol. A, Part 5)
+ *
+ * When a list of symmetry operations is given, it must contain
+ * a complete set of coordinate representatives which generates
+ * all the operations of the space group by the addition of
+ * all primitive translations of the space group. Such
+ * representatives are to be found as the coordinates of
+ * the general-equivalent position in International Tables for
+ * Crystallography Vol. A (2002), to which it is necessary to
+ * add any centring translations shown above the
+ * general-equivalent position.
+ *
+ * That is to say, it is necessary to list explicitly all the
+ * symmetry operations required to generate all the atoms in
+ * the unit cell defined by the setting used.
+ */
+ operation_xyz: str,
+ },
+ /**
+ * The CATEGORY of data items used to specify the geometry bonds in the
+ * structural model as derived from the atomic sites.
+ */
+ geom_bond: {
+ /**
+ * This label is a unique identifier for a particular site in the
+ * asymmetric unit of the crystal unit cell.
+ */
+ atom_site_label_1: str,
+ /**
+ * This label is a unique identifier for a particular site in the
+ * asymmetric unit of the crystal unit cell.
+ */
+ atom_site_label_2: str,
+ /**
+ * Intramolecular bond distance between the sites identified
+ * by _geom_bond.id
+ */
+ distance: float,
+ /**
+ * This code signals whether the angle is referred to in a
+ * publication or should be placed in a table of significant angles.
+ */
+ publ_flag: str,
+ /**
+ * The set of data items which specify the symmetry operation codes
+ * which must be applied to the atom sites involved in the geometry angle.
+ *
+ * The symmetry code of each atom site as the symmetry-equivalent position
+ * number 'n' and the cell translation number 'pqr'. These numbers are
+ * combined to form the code 'n pqr' or n_pqr.
+ *
+ * The character string n_pqr is composed as follows:
+ *
+ * n refers to the symmetry operation that is applied to the
+ * coordinates stored in _atom_site.fract_xyz. It must match a
+ * number given in _symmetry_equiv.pos_site_id.
+ *
+ * p, q and r refer to the translations that are subsequently
+ * applied to the symmetry transformed coordinates to generate
+ * the atom used in calculating the angle. These translations
+ * (x,y,z) are related to (p,q,r) by the relations
+ * p = 5 + x
+ * q = 5 + y
+ * r = 5 + z
+ */
+ site_symmetry_2: str,
+ },
+ /**
+ * The CATEGORY of data items used to record details about the
+ * creation and subsequent updating of the data block.
+ */
+ audit: {
+ /**
+ * The digital object identifier (DOI) registered to identify
+ * the data set publication represented by the current
+ * datablock. This can be used as a unique identifier for
+ * the datablock so long as the code used is a valid DOI
+ * (i.e. begins with a valid publisher prefix assigned by a
+ * Registration Agency and a suffix guaranteed to be unique
+ * by the publisher) and has had its metadata deposited
+ * with a DOI Registration Agency.
+ *
+ * A DOI is a unique character string identifying any
+ * object of intellectual property. It provides a
+ * persistent identifier for an object on a digital network
+ * and permits the association of related current data in a
+ * structured extensible way. A DOI is an implementation
+ * of the Internet concepts of Uniform Resource Name and
+ * Universal Resource Locator managed according to the
+ * specifications of the International DOI Foundation (see
+ * http://www.doi.org).
+ */
+ block_doi: str,
+ },
+ /**
+ * The CATEGORY of data items recording database deposition. These data items
+ * are assigned by database managers and should only appear in a CIF if they
+ * originate from that source.
+ */
+ database_code: {
+ /**
+ * Deposition numbers assigned by the Cambridge Crystallographic
+ * Data Centre (CCDC) to files containing structural information
+ * archived by the CCDC.
+ */
+ depnum_ccdc_archive: str,
+ },
+ /**
+ * The CATEGORY of data items used to describe atom site information
+ * used in crystallographic structure studies.
+ */
+ atom_site: {
+ /**
+ * Code for type of atomic displacement parameters used for the site.
+ */
+ adp_type: str,
+ /**
+ * A standard code to signal if the site coordinates have been
+ * determined from the intensities or calculated from the geometry
+ * of surrounding sites, or have been assigned dummy coordinates.
+ */
+ calc_flag: str,
+ /**
+ * A code which identifies a cluster of atoms that show long range
+ * positional disorder but are locally ordered. Within each such
+ * cluster of atoms, _atom_site.disorder_group is used to identify
+ * the sites that are simultaneously occupied. This field is only
+ * needed if there is more than one cluster of disordered atoms
+ * showing independent local order.
+ */
+ disorder_assembly: str,
+ /**
+ * A code that identifies a group of positionally disordered atom
+ * sites that are locally simultaneously occupied. Atoms that are
+ * positionally disordered over two or more sites (e.g. the H
+ * atoms of a methyl group that exists in two orientations) can
+ * be assigned to two or more groups. Sites belonging to the same
+ * group are simultaneously occupied, but those belonging to
+ * different groups are not. A minus prefix (e.g. "-1") is used to
+ * indicate sites disordered about a special position.
+ */
+ disorder_group: str,
+ /**
+ * Atom site coordinates as fractions of the cell length values.
+ */
+ fract_x: float,
+ /**
+ * Atom site coordinates as fractions of the cell length values.
+ */
+ fract_y: float,
+ /**
+ * Atom site coordinates as fractions of the cell length values.
+ */
+ fract_z: float,
+ /**
+ * This label is a unique identifier for a particular site in the
+ * asymmetric unit of the crystal unit cell. It is made up of
+ * components, _atom_site.label_component_0 to *_6, which may be
+ * specified as separate data items. Component 0 usually matches one
+ * of the specified _atom_type.symbol codes. This is not mandatory
+ * if an _atom_site.type_symbol item is included in the atom site
+ * list. The _atom_site.type_symbol always takes precedence over
+ * an _atom_site.label in the identification of the atom type. The
+ * label components 1 to 6 are optional, and normally only
+ * components 0 and 1 are used. Note that components 0 and 1 are
+ * concatenated, while all other components, if specified, are
+ * separated by an underline character. Underline separators are
+ * only used if higher-order components exist. If an intermediate
+ * component is not used it may be omitted provided the underline
+ * separators are inserted. For example the label 'C233__ggg' is
+ * acceptable and represents the components C, 233, '', and ggg.
+ * Each label may have a different number of components.
+ */
+ label: str,
+ /**
+ * The fraction of the atom type present at this site.
+ * The sum of the occupancies of all the atom types at this site
+ * may not significantly exceed 1.0 unless it is a dummy site. The
+ * value must lie in the 99.97% Gaussian confidence interval
+ * -3u =< x =< 1 + 3u. The _enumeration.range of 0.0:1.0 is thus
+ * correctly interpreted as meaning (0.0 - 3u) =< x =< (1.0 + 3u).
+ */
+ occupancy: float,
+ /**
+ * A concatenated series of single-letter codes which indicate the
+ * refinement restraints or constraints applied to this site. This
+ * item should not be used. It has been replaced by
+ * _atom_site.refinement_flags_posn, _adp and _occupancy. It is
+ * retained in this dictionary only to provide compatibility with
+ * legacy CIFs.
+ */
+ refinement_flags: str,
+ /**
+ * The number of different sites that are generated by the
+ * application of the space-group symmetry to the coordinates
+ * given for this site. It is equal to the multiplicity given
+ * for this Wyckoff site in International Tables for Cryst.
+ * Vol. A (2002). It is equal to the multiplicity of the general
+ * position divided by the order of the site symmetry given in
+ * _atom_site.site_symmetry_order.
+ */
+ site_symmetry_multiplicity: int,
+ /**
+ * A code to identify the atom specie(s) occupying this site.
+ * This code must match a corresponding _atom_type.symbol. The
+ * specification of this code is optional if component_0 of the
+ * _atom_site.label is used for this purpose. See _atom_type.symbol.
+ */
+ type_symbol: str,
+ /**
+ * Isotropic atomic displacement parameter, or equivalent isotropic
+ * atomic displacement parameter, U(equiv), in angstroms squared,
+ * calculated from anisotropic atomic displacement parameters.
+ *
+ * U(equiv) = (1/3) sum~i~[sum~j~(U^ij^ a*~i~ a*~j~ a~i~ a~j~)]
+ *
+ * a = the real-space cell lengths
+ * a* = the reciprocal-space cell lengths
+ * Ref: Fischer, R. X. & Tillmanns, E. (1988). Acta Cryst. C44, 775-776.
+ */
+ U_iso_or_equiv: float,
+ },
+ /**
+ * The CATEGORY of data items used to describe the anisotropic
+ * thermal parameters of the atomic sites in a crystal structure.
+ */
+ atom_site_aniso: {
+ /**
+ * Anisotropic atomic displacement parameters are usually looped in
+ * a separate list. If this is the case, this code must match the
+ * _atom_site.label of the associated atom in the atom coordinate
+ * list and conform with the same rules described in _atom_site.label.
+ */
+ label: str,
+ /**
+ * These are the standard anisotropic atomic displacement
+ * components in angstroms squared which appear in the
+ * structure factor term:
+ *
+ * T = exp{-2pi^2^ sum~i~ [sum~j~ (U^ij^ h~i~ h~j~ a*~i~ a*~j~) ] }
+ *
+ * h = the Miller indices
+ * a* = the reciprocal-space cell lengths
+ *
+ * The unique elements of the real symmetric matrix are entered by row.
+ */
+ U_11: float,
+ /**
+ * These are the standard anisotropic atomic displacement
+ * components in angstroms squared which appear in the
+ * structure factor term:
+ *
+ * T = exp{-2pi^2^ sum~i~ [sum~j~ (U^ij^ h~i~ h~j~ a*~i~ a*~j~) ] }
+ *
+ * h = the Miller indices
+ * a* = the reciprocal-space cell lengths
+ *
+ * The unique elements of the real symmetric matrix are entered by row.
+ */
+ U_12: float,
+ /**
+ * These are the standard anisotropic atomic displacement
+ * components in angstroms squared which appear in the
+ * structure factor term:
+ *
+ * T = exp{-2pi^2^ sum~i~ [sum~j~ (U^ij^ h~i~ h~j~ a*~i~ a*~j~) ] }
+ *
+ * h = the Miller indices
+ * a* = the reciprocal-space cell lengths
+ *
+ * The unique elements of the real symmetric matrix are entered by row.
+ */
+ U_13: float,
+ /**
+ * These are the standard anisotropic atomic displacement
+ * components in angstroms squared which appear in the
+ * structure factor term:
+ *
+ * T = exp{-2pi^2^ sum~i~ [sum~j~ (U^ij^ h~i~ h~j~ a*~i~ a*~j~) ] }
+ *
+ * h = the Miller indices
+ * a* = the reciprocal-space cell lengths
+ *
+ * The unique elements of the real symmetric matrix are entered by row.
+ */
+ U_22: float,
+ /**
+ * These are the standard anisotropic atomic displacement
+ * components in angstroms squared which appear in the
+ * structure factor term:
+ *
+ * T = exp{-2pi^2^ sum~i~ [sum~j~ (U^ij^ h~i~ h~j~ a*~i~ a*~j~) ] }
+ *
+ * h = the Miller indices
+ * a* = the reciprocal-space cell lengths
+ *
+ * The unique elements of the real symmetric matrix are entered by row.
+ */
+ U_23: float,
+ /**
+ * These are the standard anisotropic atomic displacement
+ * components in angstroms squared which appear in the
+ * structure factor term:
+ *
+ * T = exp{-2pi^2^ sum~i~ [sum~j~ (U^ij^ h~i~ h~j~ a*~i~ a*~j~) ] }
+ *
+ * h = the Miller indices
+ * a* = the reciprocal-space cell lengths
+ *
+ * The unique elements of the real symmetric matrix are entered by row.
+ */
+ U_33: float,
+ },
+ /**
+ * The CATEGORY of data items used to describe atomic type information
+ * used in crystallographic structure studies.
+ */
+ atom_type: {
+ /**
+ * A description of the atom(s) designated by this atom type. In
+ * most cases this will be the element name and oxidation state of
+ * a single atom species. For disordered or nonstoichiometric
+ * structures it will describe a combination of atom species.
+ */
+ description: str,
+ /**
+ * The identity of the atom specie(s) representing this atom type.
+ * Normally this code is the element symbol followed by the charge
+ * if there is one. The symbol may be composed of any character except
+ * an underline or a blank, with the proviso that digits designate an
+ * oxidation state and must be followed by a + or - character.
+ */
+ symbol: str,
+ },
+ /**
+ * The CATEGORY of data items used to describe atomic scattering
+ * information used in crystallographic structure studies.
+ */
+ atom_type_scat: {
+ /**
+ * The imaginary component of the anomalous dispersion scattering factors
+ * for this atom type and radiation by _diffrn_radiation_wavelength.value
+ */
+ dispersion_imag: float,
+ /**
+ * The real component of the anomalous dispersion scattering factors
+ * for this atom type and radiation by _diffrn_radiation_wavelength.value
+ */
+ dispersion_real: float,
+ /**
+ * Reference to source of scattering factors used for this atom type.
+ */
+ source: str,
+ },
+}
+
+export const cifCore_Aliases = {
+ 'space_group.name_H-M_full': [
+ 'symmetry_space_group_name_H-M',
+ ],
+ 'space_group_symop.operation_xyz': [
+ 'symmetry_equiv_pos_as_xyz',
+ ],
+ 'geom_bond.atom_site_label_1': [
+ 'geom_bond_atom_site_id_1',
+ ],
+ 'geom_bond.atom_site_label_2': [
+ 'geom_bond_atom_site_id_2',
+ ],
+ 'geom_bond.distance': [
+ 'geom_bond_dist',
+ ],
+ 'atom_site.adp_type': [
+ 'atom_site_thermal_displace_type',
+ ],
+ 'atom_site.label': [
+ 'atom_site_id',
+ ],
+ 'atom_site.site_symmetry_multiplicity': [
+ 'atom_site_symmetry_multiplicity',
+ ],
+ 'atom_site_aniso.label': [
+ 'atom_site_anisotrop_id',
+ ],
+ 'atom_site_aniso.U_11': [
+ 'atom_site_anisotrop_U_11',
+ ],
+ 'atom_site_aniso.U_12': [
+ 'atom_site_anisotrop_U_12',
+ ],
+ 'atom_site_aniso.U_13': [
+ 'atom_site_anisotrop_U_13',
+ ],
+ 'atom_site_aniso.U_22': [
+ 'atom_site_anisotrop_U_22',
+ ],
+ 'atom_site_aniso.U_23': [
+ 'atom_site_anisotrop_U_23',
+ ],
+ 'atom_site_aniso.U_33': [
+ 'atom_site_anisotrop_U_33',
+ ],
+}
+
+export type cifCore_Schema = typeof cifCore_Schema;
+export interface cifCore_Database extends Database<cifCore_Schema> {}
\ No newline at end of file
diff --git a/src/mol-io/reader/cif/text/parser.ts b/src/mol-io/reader/cif/text/parser.ts
index 476fb0fa76473170e697c47786f1d37ec846060b..c593e25ddf4d176b39f2fc289da025058a34687c 100644
--- a/src/mol-io/reader/cif/text/parser.ts
+++ b/src/mol-io/reader/cif/text/parser.ts
@@ -1,7 +1,8 @@
/**
- * Copyright (c) 2017 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2017-2019 mol* contributors, licensed under MIT, See LICENSE file for more info.
*
* @author David Sehnal <david.sehnal@gmail.com>
+ * @author Alexander Rose <alexander.rose@weirdbyte.de>
*/
/**
@@ -23,7 +24,7 @@
*/
import * as Data from '../data-model'
-import { Tokens, TokenBuilder } from '../../common/text/tokenizer'
+import { Tokens, TokenBuilder, Tokenizer } from '../../common/text/tokenizer'
import { ReaderResult as Result } from '../../result'
import { Task, RuntimeContext, chunkedSubtask } from '../../../../mol-task'
@@ -46,6 +47,8 @@ interface TokenizerState {
position: number,
length: number,
isEscaped: boolean,
+ isImportGet: boolean,
+ inSaveFrame: boolean,
lineNumber: number,
tokenType: CifTokenType,
@@ -168,6 +171,23 @@ function eatMultiline(state: TokenizerState) {
return prev;
}
+function eatImportGet(state: TokenizerState) {
+ // _import.get [{'save':orient_matrix 'file':templ_attr.cif}]
+ // skipWhitespace(state)
+ while (state.position < state.length) {
+ switch (state.data.charCodeAt(state.position)) {
+ case 93: // ]
+ ++state.position;
+ state.tokenEnd = state.position;
+ state.isImportGet = false
+ return;
+ default:
+ ++state.position;
+ break;
+ }
+ }
+}
+
/**
* Skips until \n or \r occurs -- therefore the newlines get handled by the "skipWhitespace" function.
*/
@@ -274,6 +294,25 @@ function isLoop(state: TokenizerState): boolean {
return true;
}
+function isImportGet(state: TokenizerState): boolean {
+ // _import.get [{'save':orient_matrix 'file':templ_attr.cif}]
+
+ if (state.tokenEnd - state.tokenStart !== 11) return false;
+
+ if (state.data.charCodeAt(state.tokenStart + 1) !== 105) return false; // i
+ if (state.data.charCodeAt(state.tokenStart + 2) !== 109) return false; // m
+ if (state.data.charCodeAt(state.tokenStart + 3) !== 112) return false; // p
+ if (state.data.charCodeAt(state.tokenStart + 4) !== 111) return false; // o
+ if (state.data.charCodeAt(state.tokenStart + 5) !== 114) return false; // r
+ if (state.data.charCodeAt(state.tokenStart + 6) !== 116) return false; // t
+ if (state.data.charCodeAt(state.tokenStart + 7) !== 46) return false; // .
+ if (state.data.charCodeAt(state.tokenStart + 8) !== 103) return false; // g
+ if (state.data.charCodeAt(state.tokenStart + 9) !== 101) return false; // e
+ if (state.data.charCodeAt(state.tokenStart + 10) !== 116) return false; // t
+
+ return true;
+}
+
/**
* Checks if the current token shares the namespace with string at <start,end).
*/
@@ -315,6 +354,17 @@ function getNamespace(state: TokenizerState, endIndex: number) {
return state.data.substring(state.tokenStart, endIndex);
}
+/**
+ * Returns true if the current token contain no '.', otherwise returns false.
+ */
+function isFlatNamespace(state: TokenizerState): boolean {
+ let i: number;
+ for (i = state.tokenStart; i < state.tokenEnd; ++i) {
+ if (state.data.charCodeAt(i) === 46) return false;
+ }
+ return true;
+}
+
/**
* String representation of the current token.
*/
@@ -336,6 +386,7 @@ function moveNextInternal(state: TokenizerState) {
state.tokenStart = state.position;
state.tokenEnd = state.position;
state.isEscaped = false;
+
let c = state.data.charCodeAt(state.position);
switch (c) {
case 35: // #, comment
@@ -357,20 +408,28 @@ function moveNextInternal(state: TokenizerState) {
state.tokenType = CifTokenType.Value;
break;
default:
- eatValue(state);
+ if (state.isImportGet) {
+ eatImportGet(state);
+ } else {
+ eatValue(state);
+ }
+
// escaped is always Value
if (state.isEscaped) {
state.tokenType = CifTokenType.Value;
- // _ always means column name
+ // _ means column name, including _import.get
} else if (state.data.charCodeAt(state.tokenStart) === 95) { // _
+ if (state.inSaveFrame && isImportGet(state)) {
+ state.isImportGet = true
+ }
state.tokenType = CifTokenType.ColumnName;
- // 5th char needs to be _ for data_ or loop_
+ // 5th char needs to be _ for data_, save_ or loop_
} else if (state.tokenEnd - state.tokenStart >= 5 && state.data.charCodeAt(state.tokenStart + 4) === 95) {
if (isData(state)) state.tokenType = CifTokenType.Data;
else if (isSave(state)) state.tokenType = CifTokenType.Save;
else if (isLoop(state)) state.tokenType = CifTokenType.Loop;
else state.tokenType = CifTokenType.Value;
- // all other tests failed, we are at Value token.
+ // all other tests failed, we are at Value token.
} else {
state.tokenType = CifTokenType.Value;
}
@@ -396,6 +455,8 @@ function createTokenizer(data: string, runtimeCtx: RuntimeContext): TokenizerSta
tokenType: CifTokenType.End,
lineNumber: 1,
isEscaped: false,
+ isImportGet: false,
+ inSaveFrame: false,
runtimeCtx
};
@@ -410,13 +471,48 @@ interface CifCategoryResult {
errorMessage: string;
}
+interface CifCategoryData {
+ name: string,
+ rowCount: number,
+ fieldNames: string[],
+ fields: { [name: string]: Data.CifField }
+}
+
type FrameContext = {
categoryNames: string[],
- categories: { [name: string]: Data.CifCategory }
+ categoryData: { [name: string]: CifCategoryData }
}
function FrameContext(): FrameContext {
- return { categoryNames: [], categories: Object.create(null) };
+ return { categoryNames: [], categoryData: Object.create(null) };
+}
+
+function CifCategories(categoryNames: string[], categoryData: { [name: string]: CifCategoryData }): { [name: string]: Data.CifCategory } {
+ const categories = Object.create(null)
+ for (const name of categoryNames) {
+ const d = categoryData[name]
+ categories[name] = Data.CifCategory(d.name, d.rowCount, d.fieldNames, d.fields)
+ }
+ return categories
+}
+
+function CifBlock(ctx: FrameContext, header: string, saveFrames?: Data.CifFrame[]): Data.CifBlock {
+ return Data.CifBlock(ctx.categoryNames, CifCategories(ctx.categoryNames, ctx.categoryData), header, saveFrames)
+}
+
+function CifSaveFrame(ctx: FrameContext, header: string): Data.CifBlock {
+ return Data.CifBlock(ctx.categoryNames, CifCategories(ctx.categoryNames, ctx.categoryData), header)
+}
+
+function addFields(ctx: FrameContext, name: string, rowCount: number, fieldNames: string[], fields: { [k: string]: Data.CifField }) {
+ if (name in ctx.categoryData) {
+ const cat = ctx.categoryData[name]
+ cat.fieldNames.push(...fieldNames)
+ Object.assign(cat.fields, fields)
+ } else {
+ ctx.categoryData[name] = { name, rowCount, fieldNames, fields };
+ ctx.categoryNames.push(name);
+ }
}
/**
@@ -449,9 +545,7 @@ function handleSingle(tokenizer: TokenizerState, ctx: FrameContext): CifCategory
moveNext(tokenizer);
}
- const catName = name.substr(1);
- ctx.categories[catName] = Data.CifCategory(catName, 1, fieldNames, fields);
- ctx.categoryNames.push(catName);
+ addFields(ctx, name.substr(1), 1, fieldNames, fields)
return {
hasError: false,
@@ -496,10 +590,13 @@ async function handleLoop(tokenizer: TokenizerState, ctx: FrameContext): Promise
moveNext(tokenizer);
const name = getNamespace(tokenizer, getNamespaceEnd(tokenizer));
+ const isFlat = isFlatNamespace(tokenizer);
const fieldNames: string[] = [];
while (tokenizer.tokenType === CifTokenType.ColumnName) {
- fieldNames[fieldNames.length] = getTokenString(tokenizer).substring(name.length + 1);
+ fieldNames[fieldNames.length] = isFlat
+ ? getTokenString(tokenizer)
+ : getTokenString(tokenizer).substring(name.length + 1);
moveNext(tokenizer);
}
@@ -526,14 +623,19 @@ async function handleLoop(tokenizer: TokenizerState, ctx: FrameContext): Promise
}
const rowCount = (state.tokenCount / fieldCount) | 0;
- const fields = Object.create(null);
- for (let i = 0; i < fieldCount; i++) {
- fields[fieldNames[i]] = Data.CifField.ofTokens(tokens[i]);
- }
+ if (isFlat) {
+ for (let i = 0; i < fieldCount; i++) {
+ const fields = { '': Data.CifField.ofTokens(tokens[i]) };
+ addFields(ctx, fieldNames[i].substr(1), rowCount, [''], fields)
+ }
+ } else {
+ const fields = Object.create(null);
+ for (let i = 0; i < fieldCount; i++) {
+ fields[fieldNames[i]] = Data.CifField.ofTokens(tokens[i]);
+ }
- const catName = name.substr(1);
- ctx.categories[catName] = Data.CifCategory(catName, rowCount, fieldNames, fields);
- ctx.categoryNames.push(catName);
+ addFields(ctx, name.substr(1), rowCount, fieldNames, fields)
+ }
return {
hasError: false,
@@ -568,12 +670,14 @@ async function parseInternal(data: string, runtimeCtx: RuntimeContext) {
let blockCtx = FrameContext();
- let inSaveFrame = false;
-
// the next three initial values are never used in valid files
let saveFrames: Data.CifFrame[] = [];
let saveCtx = FrameContext();
- let saveFrame: Data.CifFrame = Data.CifSafeFrame(saveCtx.categoryNames, saveCtx.categories, '');
+ let saveFrame: Data.CifFrame = Data.CifSaveFrame(
+ saveCtx.categoryNames, CifCategories(saveCtx.categoryNames, saveCtx.categoryData), ''
+ );
+
+ let saveHeader = ''
runtimeCtx.update({ message: 'Parsing...', current: 0, max: data.length });
@@ -583,11 +687,11 @@ async function parseInternal(data: string, runtimeCtx: RuntimeContext) {
// Data block
if (token === CifTokenType.Data) {
- if (inSaveFrame) {
+ if (tokenizer.inSaveFrame) {
return error(tokenizer.lineNumber, 'Unexpected data block inside a save frame.');
}
if (blockCtx.categoryNames.length > 0) {
- dataBlocks.push(Data.CifBlock(blockCtx.categoryNames, blockCtx.categories, blockHeader, saveFrames));
+ dataBlocks.push(CifBlock(blockCtx, blockHeader, saveFrames));
}
blockHeader = data.substring(tokenizer.tokenStart + 5, tokenizer.tokenEnd);
blockCtx = FrameContext();
@@ -595,47 +699,47 @@ async function parseInternal(data: string, runtimeCtx: RuntimeContext) {
moveNext(tokenizer);
// Save frame
} else if (token === CifTokenType.Save) {
- const saveHeader = data.substring(tokenizer.tokenStart + 5, tokenizer.tokenEnd);
- if (saveHeader.length === 0) {
+ if (tokenizer.tokenEnd - tokenizer.tokenStart === 5) { // end of save frame
if (saveCtx.categoryNames.length > 0) {
- saveFrames[saveFrames.length] = saveFrame;
+ saveFrames[saveFrames.length] = CifSaveFrame(saveCtx, saveHeader);
}
- inSaveFrame = false;
- } else {
- if (inSaveFrame) {
+ tokenizer.inSaveFrame = false;
+ } else { // start of save frame
+ if (tokenizer.inSaveFrame) {
return error(tokenizer.lineNumber, 'Save frames cannot be nested.');
}
- inSaveFrame = true;
- const safeHeader = data.substring(tokenizer.tokenStart + 5, tokenizer.tokenEnd);
+ tokenizer.inSaveFrame = true;
+ saveHeader = data.substring(tokenizer.tokenStart + 5, tokenizer.tokenEnd);
saveCtx = FrameContext();
- saveFrame = Data.CifSafeFrame(saveCtx.categoryNames, saveCtx.categories, safeHeader);
+ // saveFrame = CifSaveFrame(saveCtx, saveHeader);
}
moveNext(tokenizer);
// Loop
} else if (token === CifTokenType.Loop) {
- const cat = await handleLoop(tokenizer, inSaveFrame ? saveCtx : blockCtx);
+ const cat = await handleLoop(tokenizer, tokenizer.inSaveFrame ? saveCtx : blockCtx);
if (cat.hasError) {
return error(cat.errorLine, cat.errorMessage);
}
// Single row
} else if (token === CifTokenType.ColumnName) {
- const cat = handleSingle(tokenizer, inSaveFrame ? saveCtx : blockCtx);
+ const cat = handleSingle(tokenizer, tokenizer.inSaveFrame ? saveCtx : blockCtx);
if (cat.hasError) {
return error(cat.errorLine, cat.errorMessage);
}
// Out of options
} else {
+ console.log(tokenizer.tokenType, Tokenizer.getTokenString(tokenizer))
return error(tokenizer.lineNumber, 'Unexpected token. Expected data_, loop_, or data name.');
}
}
// Check if the latest save frame was closed.
- if (inSaveFrame) {
+ if (tokenizer.inSaveFrame) {
return error(tokenizer.lineNumber, `Unfinished save frame (${saveFrame.header}).`);
}
if (blockCtx.categoryNames.length > 0 || saveFrames.length > 0) {
- dataBlocks.push(Data.CifBlock(blockCtx.categoryNames, blockCtx.categories, blockHeader, saveFrames));
+ dataBlocks.push(CifBlock(blockCtx, blockHeader, saveFrames));
}
return result(Data.CifFile(dataBlocks));
diff --git a/src/mol-model-formats/structure/_spec/cif-core.spec.ts b/src/mol-model-formats/structure/_spec/cif-core.spec.ts
new file mode 100644
index 0000000000000000000000000000000000000000..5e73efda9e8e6ef5d64c39ccb4e10e585ae27c81
--- /dev/null
+++ b/src/mol-model-formats/structure/_spec/cif-core.spec.ts
@@ -0,0 +1,70 @@
+/**
+ * Copyright (c) 2019 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ *
+ * @author Alexander Rose <alexander.rose@weirdbyte.de>
+ */
+
+import { CIF } from '../../../mol-io/reader/cif';
+
+const cifCoreString = `data_n1379
+_audit_block_doi 10.5517/ccy42jn
+_database_code_depnum_ccdc_archive 'CCDC 867861'
+loop_
+_citation_id
+_citation_doi
+_citation_year
+1 10.1002/chem.201202070 2012
+_audit_update_record
+;
+2012-02-20 deposited with the CCDC.
+2016-10-08 downloaded from the CCDC.
+;
+
+loop_
+_atom_type_symbol
+_atom_type_description
+_atom_type_scat_dispersion_real
+_atom_type_scat_dispersion_imag
+_atom_type_scat_source
+C C 0.0181 0.0091 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+H H 0.0000 0.0000 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+N N 0.0311 0.0180 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+O O 0.0492 0.0322 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+F F 0.0727 0.0534 'International Tables Vol C Tables 4.2.6.8 and 6.1.1.4'
+
+_cell_length_a 11.0829(8)
+_cell_length_b 14.6829(10)
+_cell_length_c 16.8532(17)
+_cell_angle_alpha 105.728(6)
+_cell_angle_beta 100.310(6)
+_cell_angle_gamma 110.620(4)
+_cell_volume 2353.3(3)
+_cell_formula_units_Z 1
+_cell_measurement_temperature 100(2)
+_cell_measurement_reflns_used 5934
+_cell_measurement_theta_min 2.86
+_cell_measurement_theta_max 64.30
+`
+
+describe('cif-core read', () => {
+ it('frame', async () => {
+ const parsed = await CIF.parseText(cifCoreString).run()
+ if (parsed.isError) return
+ const cifFile = parsed.result
+ const block = cifFile.blocks[0]
+
+ expect(block.getField('cell_length_a')!.float(0)).toBe(11.0829)
+ expect.assertions(1)
+ });
+
+ it('schema', async () => {
+ const parsed = await CIF.parseText(cifCoreString).run()
+ if (parsed.isError) return
+ const cifFile = parsed.result
+ const block = cifFile.blocks[0]
+ const cifCore = CIF.schema.cifCore(block)
+
+ expect(cifCore.cell.length_a.value(0)).toBe(11.0829)
+ expect.assertions(1)
+ });
+});
\ No newline at end of file