RetroSearch Browse

.Config().IsFormatGBSeq() && !

.Config().IsFormatINSDSeq()) {

124

m_CommentInternalIndent(0),

139

m_CommentInternalIndent(0),

156

m_CommentInternalIndent(0),

182 if

( ends_with_ellipsis ) {

197 const string

& next_comment_first_string = next_comment.

m_Comment

.front();

198 bool

next_comment_starts_with_empty_line =

false

;

199 ITERATE

(

string

, next_com_line_it, next_comment_first_string ) {

200 const char

ch = *next_com_line_it;

202

next_comment_starts_with_empty_line =

true

;

209 if

( ! next_comment_starts_with_empty_line ) {

216 string

& last_str_of_comment =

m_Comment

.back();

217 if

( last_str_of_comment.empty() ) {

221

string::size_type pos = (last_str_of_comment.length() - 1);

222 if

( last_str_of_comment[pos] ==

'\n'

) {

227 for

( ; pos < last_str_of_comment.length(); --pos ) {

228 const char

ch = last_str_of_comment[pos];

232

last_str_of_comment.erase(pos);

254 static const string

kNsAreGaps =

"The strings of n's in this record represent "

255 "gaps between contigs, and the length of each string corresponds "

256 "to the length of the gap."

;

277

seglist.push_back(

TAln

(&aln) );

296 static const string

tpa_string =

297 "THIRD PARTY DATABASE: This TPA record uses data from DDBJ/EMBL/GenBank "

;

299 if

( !

.IsTPA() ||

.IsRefSeq() ) {

313

vector<string> histaccns;

324 if

(other_id->

IsGi

()) {

333 if

(other_id->

IsGi

()) {

344 if

( !tid.empty() ) {

348 if

( histaccns.empty() ) {

352 sort

( histaccns.begin(), histaccns.end() );

353

histaccns.erase( unique( histaccns.begin(), histaccns.end() ), histaccns.end() );

356 text

<< tpa_string << ((histaccns.size() > 1) ?

"entries "

"entry "

);

358 size_t size

= histaccns.size();

361 for

(

size_t i

= 0;

size

; ) {

362 text

<< histaccns[

];

365 text

<< ((

) ?

" and "

", "

);

373

vector<string> accessions;

381 if

( !(*ufi)->CanGetData() || !(*ufi)->GetData().IsStr() ||

382

!(*ufi)->CanGetLabel() ) {

386 if

( oid.

IsStr

() &&

388 string

acc = (*ufi)->GetData().

();

389 if

( !acc.empty() ) {

395 if

( accessions.empty() ) {

400 text

<< tpa_string << ((accessions.size() > 1) ?

"entries "

"entry "

);

402 size_t size

= accessions.size();

405 for

(

size_t i

= 0;

size

; ) {

406 text

<< accessions[

];

409 text

<< ((

) ?

" and "

", "

);

424 const string

*uvc =

nullptr

, *bic =

nullptr

, *smc =

nullptr

;

426 if

( uo.

(

"UniVecComment"

) ) {

432 if

( uo.

(

"AdditionalComment"

) ) {

438 if

( uo.

(

"SmartComment"

) && dump_mode ) {

448 text

<< pfx <<

"Vector Explanation: "

<< *uvc;

452 text

<< pfx <<

"Bankit Comment: "

<< *bic;

456 text

<< pfx <<

"Bankit Comment: "

<< *smc;

470

vector<string> assembly_pieces;

472 if

( uo.

(

"Assembly"

) ) {

481 if

( !(*fit)->GetData().IsFields() ) {

495

(*fit)->GetData().GetFields())

504 if

(

"accession"

) {

506

}

else if

(

"name"

) {

510 if

(

"gi"

) {

515

}

else if

(

"from"

) {

517

}

else if

(

"to"

) {

523 if

( ! accession.empty() ) {

538 ctx

.Config().GetHTMLFormatter().FormatGeneralId(oss, accession);

543 if

( from > 0 && to > 0 ) {

544

oss <<

" (range: "

<< from <<

"-"

<< to <<

")"

;

547 string

new_piece = oss.str();

548

assembly_pieces.push_back( new_piece );

549

}

else if

( ! name.empty() ) {

550

assembly_pieces.push_back( name );

555 if

( ! assembly_pieces.empty() ) {

557

oss <<

" The reference sequence was derived from "

;

559 size_t

assembly_size = assembly_pieces.size();

560 for

(

size_t

ii = 0; ii < assembly_size; ++ii ) {

562

oss << ((ii < assembly_size - 1) ?

", "

" and "

);

564

oss << assembly_pieces[ii];

620 bool

is_html =

.Config().DoHTML();

635 if

( uo.

(

"Collaborator"

) ) {

643 if

( uo.

(

"GenomicSource"

) ) {

650 string

identical_to_start;

651 string

identical_to_end;

655 enum

EIdenticalToPriority {

656

eIdenticalToPriority_Nothing = 1,

657

eIdenticalToPriority_Gi,

658

eIdenticalToPriority_Name,

659

eIdenticalToPriority_Accn

661 int

identical_to_priority = eIdenticalToPriority_Nothing;

663 if

(uo.

(

"IdenticalTo"

)) {

666 if

( !(*it)->GetData().IsFields() ) {

677 if

(sub.

GetLabel

().

() ==

"accession"

&& identical_to_priority <= eIdenticalToPriority_Accn ) {

679

identical_to_priority = eIdenticalToPriority_Accn;

681 if

(sub.

GetLabel

().

() ==

"name"

&& identical_to_priority <= eIdenticalToPriority_Name ) {

683

identical_to_priority = eIdenticalToPriority_Name;

685 if

(sub.

GetLabel

().

() ==

"gi"

&& identical_to_priority <= eIdenticalToPriority_Gi ) {

686

identical_to =

"gi:"

688

identical_to_priority = eIdenticalToPriority_Gi;

700

oss << status_str <<

' ' 705

oss <<

" This record is predicted by genome sequence analysis and is " 706

"not yet supported by experimental evidence."

;

710 if

( !build_num.empty() ) {

711

oss <<

" Features on this sequence have been produced for build " 712

<< build_num <<

" of the NCBI's genome annotation" 717

oss <<

"documentation"

;

723

oss <<

" NCBI contigs are derived from assembled genomic sequence data.~" 725

" Documentation of NCBI's Annotation Process "

;

730 if

(collaborator.empty()) {

731

oss <<

" This record has not yet been subject to final NCBI review."

;

733

oss <<

" This record is based on preliminary " 734 "annotation provided by "

<< collaborator <<

'.'

;

738

oss <<

" This record has not been reviewed and the function is unknown."

;

741

oss <<

" This record has undergone validation or preliminary review."

;

744

oss <<

" This record has been curated by " 745

<< (collaborator.empty() ?

"NCBI staff"

: collaborator) <<

'.'

;

748

oss <<

" This record is predicted by automated computational analysis."

;

751

oss <<

" This record is provided to represent a collection of " 752

"whole genome shotgun sequences."

;

755

oss <<

" This record is provided to represent a collection of " 756

"transcriptome shotgun assembly sequences."

;

764

!collaborator.empty() ) {

765

oss <<

" This record has been curated by "

<< collaborator <<

'.'

;

768 if

( !

.empty() ) {

769

oss <<

" This record is derived from an annotated genomic sequence (" 773 if

( !identical_to.empty() ) {

774

oss <<

" The reference sequence is identical to "

;

775 const bool

add_link = (is_html && identical_to_priority != eIdenticalToPriority_Name);

777 ctx

.Config().GetHTMLFormatter().FormatGeneralId(oss, identical_to);

783 if

( ! identical_to_start.empty() && ! identical_to_end.empty() ) {

784

oss <<

" (range: "

<< identical_to_start <<

"-"

785

identical_to_end <<

")"

;

797 const static string

kRefSeqGeneLink =

"<a href=\"https://www.ncbi.nlm.nih.gov/refseq/rsg/\">RefSeqGene</a>"

;

798 const static string

kRefSeqGene =

"RefSeqGene"

;

802

desc_it; ++desc_it) {

807 if

(

->GetData().IsStr()) {

808 const string

& status1 =

->GetData().GetStr();

809 if

(status1 ==

"Reference Standard"

) {

810

oss <<

"~This sequence is a reference standard in the " 811

<< (is_html ? kRefSeqGeneLink : kRefSeqGene)

831

ostringstream result_oss;

833 const static string

kRefSeqCat =

"RefSeq Category"

;

836

result_oss << kRefSeqCat <<

": "

;

838 if

( pCategoryField &&

841 const string

& sCategory = pCategoryField->

GetData

().

();

842

result_oss << sCategory <<

'\n'

;

844

result_oss <<

"(?UNKNOWN?)"

'\n'

;

851 if

( pDetailsField ) {

855 const static char

* arrFieldNames[] = {

856 "CALC"

"CCA"

"CLI"

"COM"

"FGS"

"MOD"

"PHY"

"PRT"

"QfO"

"TYS"

"UPR" 860 const CTempString

sFieldName( arrFieldNames[field_idx] );

862

field_name += sFieldName;

865

mapFieldNameToRef.

find

(field_name);

866 if

( find_iter == mapFieldNameToRef.

end

() ) {

877 if

( sFieldName.

length

() < kRefSeqCat.length() ) {

879

(kRefSeqCat.length() - sFieldName.

length

()),

' '

);

882

result_oss << sFieldName <<

": " 883

<< find_iter->second->GetData().GetStr() <<

'\n'

;

887 return

result_oss.str();

894 static const string

default_str =

"?"

;

896 if

.IsWGSMaster()) {

900 const string

& wgsaccn =

.GetWGSMasterAccn();

901 const string

& wgsname =

.GetWGSMasterName();

907 const string

* taxname = &default_str;

916 const string

= &default_str, *

= &default_str;

921 if

(uo.

(

"WGS_accession_first"

)) {

928 if

(uo.

(

"WGS_accession_last"

)) {

946 text

"The "

<< *taxname

947

" whole genome shotgun (WGS) project has the project accession " 948

<< wgsaccn <<

". This version of the project ("

version 949

") has the accession number "

<< wgsname <<

","

;

951 text

" and consists of sequences "

<< *

"-"

<< *

"."

;

953 text

" and consists of sequence "

<< *

"."

;

961 static const string

default_str =

"?"

;

963 if

.IsTSAMaster()) {

967 const string

& tsaaccn =

.GetTSAMasterAccn();

968 const string

& tsaname =

.GetTSAMasterName();

974 const string

* taxname = &default_str;

983 const string

= &default_str, *

= &default_str;

990 if

(uo.

(

"Accession_first"

)) {

996

}

else if

(uo.

(

"TSA_accession_first"

)) {

1003 if

(uo.

(

"Accession_last"

)) {

1009

}

else if

(uo.

(

"TSA_accession_last"

)) {

1022

ostringstream

;

1023 text

"The "

<< *taxname

1024

" transcriptome shotgun assembly (TSA) project has the project accession " 1025

<< tsaaccn <<

". This version of the project ("

version 1026

") has the accession number "

<< tsaname <<

","

;

1028 text

" and consists of sequences "

<< *

"-"

<< *

"."

;

1030 text

" and consists of sequence "

<< *

"."

;

1038 static const string

default_str =

"?"

;

1040 if

.IsTLSMaster()) {

1044 const string

& tlsaccn =

.GetTLSMasterAccn();

1045 const string

& tlsname =

.GetTLSMasterName();

1051 const string

* taxname = &default_str;

1060 const string

= &default_str, *

= &default_str;

1066 if

(uo.

(

"TLS_accession_first"

)) {

1073 if

(uo.

(

"TLS_accession_last"

)) {

1086

ostringstream

;

1087 text

"The "

<< *taxname

1088

" targeted locus study (TLS) project has the project accession " 1089

<< tlsaccn <<

". This version of the project ("

version 1090

") has the accession number "

<< tlsname <<

","

;

1092 text

" and consists of sequences "

<< *

"-"

<< *

"."

;

1094 text

" and consists of sequence "

<< *

"."

;

1104 bool

is_prot =

.IsProt();

1108 return "COMPLETENESS: full length"

;

1111 return "COMPLETENESS: not full length"

;

1114 return

(is_prot ?

"COMPLETENESS: incomplete on the amino end"

1115 "COMPLETENESS: incomplete on the 5' end"

);

1118 return

(is_prot ?

"COMPLETENESS: incomplete on the carboxy end"

1119 "COMPLETENESS: incomplete on the 3' end"

);

1122 return "COMPLETENESS: incomplete on both ends"

;

1125 return

(is_prot ?

"COMPLETENESS: complete on the amino end"

1126 "COMPLETENESS: complete on the 5' end"

);

1129 return

(is_prot ?

"COMPLETENESS: complete on the carboxy end"

1130 "COMPLETENESS: complete on the 3' end"

);

1133 return "COMPLETENESS: unknown"

;

1143 if

(

.IsDelta()) {

1147

ostringstream

;

1149 text

"* NOTE: This is a partial genome representation."

;

1151 text

" It currently~* consists of "

<< (summary.

+ 1) <<

" contigs. The true order of the pieces~" 1152

"* is not known and their order in this sequence record is~" 1153

"* arbitrary. Gaps between the contigs are represented as~" 1154

"* runs of N, but the exact sizes of the gaps are unknown."

;

1158 string

comment =

.str();

1169 if

(

.IsDelta()) {

1175

ostringstream

;

1179 text

"* NOTE: This record contains "

<< (summary.

+ 1) <<

" individual~" 1180

"* sequencing reads that have not been assembled into~" 1181

"* contigs. Runs of N are used to separate the reads~" 1182

"* and the order in which they appear is completely~" 1183

"* arbitrary. Low-pass sequence sampling is useful for~" 1184

"* identifying clones that may be gene-rich and allows~" 1185

"* overlap relationships among clones to be deduced.~" 1186

"* However, it should not be assumed that this clone~" 1187

"* will be sequenced to completion. In the event that~" 1188

"* the record is updated, the accession number will~" 1189

"* be preserved."

;

1194 text

"* NOTE: This is a \"working draft\" sequence."

;

1196 text

" It currently~" 1197

"* consists of "

<< (summary.

+ 1) <<

" contigs. The true order of the pieces~" 1198

"* is not known and their order in this sequence record is~" 1199

"* arbitrary. Gaps between the contigs are represented as~" 1200

"* runs of N, but the exact sizes of the gaps are unknown."

;

1202 text

"~* This record will be updated with the finished sequence~" 1203

"* as soon as it is available and the accession number will~" 1204

"* be preserved." 1208 text

"* NOTE: This is a \"working draft\" sequence."

;

1210 text

" It currently~* consists of "

<< (summary.

+ 1)

1211

" contigs. Gaps between the contigs~" 1212

"* are represented as runs of N. The order of the pieces~" 1213

"* is believed to be correct as given, however the sizes~" 1214

"* of the gaps between them are based on estimates that have~" 1215

"* provided by the submitter."

;

1217 text

"~* This sequence will be replaced~" 1218

"* by the finished sequence as soon as it is available and~" 1219

"* the accession number will be preserved." 1226 string

comment =

.str();

1235 const bool

bHtml =

.Config().DoHTML();

1239

ostringstream

;

1242 ctx

.Config().GetHTMLFormatter().FormatModelEvidence(me_name, me);

1244 text

"MODEL "

<< *refseq <<

": "

"This record is predicted by " 1245

"automated computational analysis. This record is derived from " 1246

"a genomic sequence ("

<< me_name <<

")"

;

1250 text

" and transcript sequence"

;

1259 ctx

.Config().GetHTMLFormatter().FormatTranscript(tr_name, *

);

1260 text

<< prefix << tr_name;

1262 if

(num_assm ==

count

+ 1) {

1271 if

( !me.

method

.empty() ) {

1272 text

" annotated using gene prediction method: "

<< me.

method

;

1276 text

", supported by "

;

1278 text

"mRNA and EST "

;

1279

}

else if

( me.

mrnaEv

) {

1285 text

"evidence"

;

1288 const char

*documentation_str = ( bHtml ?

1289 "<a href=\"https://www.ncbi.nlm.nih.gov/genome/annotation_euk/process/\">Documentation</a>"

1292 text

".~Also see:~" 1293

" "

<< documentation_str <<

" of NCBI's Annotation Process "

;

1299

(

string

& chromosome,

1300 string

& assembly_date,

1301 string

& ncbi_annotation,

1307 if

(uo.

(

"AssemblyDate"

)) {

1315 if

(uo.

(

"NcbiAnnotation"

)) {

1324 const string

* name =

nullptr

;

1329

name = &(*st)->GetName();

1344

assembly_date =

"?"

;

1347

ncbi_annotation =

"?"

;

1355 const static string

kEncodeProjLink =

"https://www.nhgri.nih.gov/10005107"

;

1357 const bool

bHtml =

.Config().DoHTML();

1359 if

.IsEncode()) {

1364 str

"REFSEQ: This record was provided by the "

;

1366 str

"<a href=\""

<< kEncodeProjLink <<

"\">"

;

1372 str

" project."

;

1374 string

chromosome, assembly_date, ncbi_annotation;

1376 str

" It is defined by coordinates on the sequence of chromosome " 1377

<< chromosome <<

" from the "

<< assembly_date

1378

" assembly of the human genome (NCBI build "

<< ncbi_annotation

1387 const bool

bHtml =

.Config().DoHTML();

1389 const string

& sAuthorizedAccess =

.GetAuthorizedAccess();

1390 if

( sAuthorizedAccess.empty() ) {

1396 str

"These data are available through the dbGaP authorized access system. "

;

1399

"https://dbgap.ncbi.nlm.nih.gov/aa/wga.cgi?adddataset=" 1400

<< sAuthorizedAccess <<

"&page=login\">"

;

1401 str

"Request access"

;

1403 str

" to Study "

;

1405

"https://www.ncbi.nlm.nih.gov/projects/gap/cgi-bin/study.cgi?study_id=" 1406

<< sAuthorizedAccess <<

"\">"

;

1407 str

<< sAuthorizedAccess;

1410 str

"Request access to Study "

;

1411 str

<< sAuthorizedAccess;

1420 const bool

bHtml =

.Config().DoHTML();

1423 if

( ! pOpticalMapPoints ||

1429 const string

& sFiletrackURL =

.GetFiletrackURL();

1431 const bool

bIsCircular =

FIELD_EQUALS

(

.GetHandle(), Inst_Topology,

1441 _ASSERT

( ! vecOfPoints.empty() );

1444 if

( bHtml && ! sFiletrackURL.empty() ) {

1445 str

"<a href=\""

<< sFiletrackURL <<

"\">"

;

1448 if

( bHtml && ! sFiletrackURL.empty() ) {

1453 size_t

uNumFrags = pOpticalMapPoints->

GetPoints

().size();

1454 if

( ! bIsCircular )

1459 if

(uNumFrags > 1 && vecOfPoints[uNumFrags-1] < uBioseqLength - 1) {

1464 str

" piece"

<< ( (uNumFrags > 1) ?

"s"

""

) <<

":"

;

1468 TSeqPos

thisEndPos = vecOfPoints[0] + 1;

1471 if

( ! bIsCircular ) {

1473 str

, prevEndPos, thisEndPos, uBioseqLength,

1476

prevEndPos = thisEndPos + 1;

1479 for

(

size_t

idx = 1; idx < vecOfPoints.size(); ++idx ) {

1480

thisEndPos = vecOfPoints[idx] + 1;

1482 str

, prevEndPos, thisEndPos, uBioseqLength,

1484

prevEndPos = thisEndPos + 1;

1489

thisEndPos = ( bIsCircular ? vecOfPoints[0] + 1 : uBioseqLength );

1490 if

( bIsCircular || prevEndPos < uBioseqLength - 1 ) {

1492 str

, prevEndPos, thisEndPos, uBioseqLength,

1503 const bool

bHtml =

.Config().DoHTML();

1505 const

vector< string > & sBasemodURLs =

.GetBasemodURLs();

1506 int

numBases = (

int

) sBasemodURLs.size();

1510 if

( numBases < 1 ) {

1514 if

( numBases == 1 ) {

1515 str

"This genome has a "

;

1519 if

( ! url.empty() ) {

1521 str

"<a href=\""

<< url <<

"\">"

"base modification file"

"</a>"

;

1525 str

"base modification file"

;

1527 str

" available."

;

1529 str

"There are "

;

1531 str

" base modification files"

;

1538 if

( ! url.empty() ) {

1541 str

<< pfx <<

"<a href=\""

<< url <<

"\">"

<< j <<

"</a>"

;

1542 if

( numBases == 2 ) {

1544

}

else if

( j == numBases - 1 ) {

1554 str

" available for this genome."

;

1562 if

( !

.IsRSUniqueProt() ) {

1571 str

"REFSEQ: This record represents a single, non-redundant, protein " 1572

"sequence which may be annotated on many different RefSeq " 1573

"genomes from the same, or different, species."

;

1608 const char

* provider,

const char

* pipeline,

const char

* status,

bool

has_name,

const char

* organism,

1609 const char

const char

* category,

const char

* accession )

1616 if

( label_str ==

"GOLD Stamp ID"

NStr::StartsWith

(data_str,

"Gi"

) ) {

1617 result

"<a href=\"http://genomesonline.org/cgi-bin/GOLD/bin/GOLDCards.cgi?goldstamp="

<< data_str

1618

"\">"

<< data_str <<

"</a>"

;

1621 if

( label_str ==

"Annotation Software Version"

) {

1622 result

"<a href=\"https://www.ncbi.nlm.nih.gov/genome/annotation_euk/release_notes/#version" 1624

"\">"

<< data_str <<

"</a>"

;

1626

}

else if

(

NStr::Equal

(label_str,

"Annotation Name"

) &&

1632 if

(

NStr::Find

(data_str,

"Updated Annotation Release"

) !=

NPOS

) {

1633 NStr::Replace

( data_str,

" Updated Annotation Release "

"/"

, fst );

1635 NStr::Replace

( data_str,

" Annotation Release "

"/"

, fst );

1639 result

"<a href=\"https://www.ncbi.nlm.nih.gov/genome/annotation_euk/" 1641

"\">"

<< data_str <<

"</a>"

;

1643 result

"<a href=\"https://www.ncbi.nlm.nih.gov/genome/annotation_euk/" 1646

"\">"

<< data_str <<

"</a>"

;

1652 NStr::Replace

( data_str,

" Annotation Release "

"/"

, fst );

1654 result

"<a href=\"https://www.ncbi.nlm.nih.gov/genome/annotation_euk/" 1656

"\">"

<< data_str <<

"</a>"

;

1659 string

accn = data_str;

1664 result

"<a href=\"https://www.ebi.ac.uk/interpro/entry/pfam/" 1666

"\">"

<< data_str <<

"</a>"

;

1671 NStr::Replace

( data_str,

"Domain architecture ID "

""

, fst );

1673 result

"<a href=\"https://www.ncbi.nlm.nih.gov/Structure/sparcle/archview.html?archid=" 1675

"\">"

<< data_str <<

"</a>"

;

1677

}

else if

(

NStr::Equal

(label_str,

"Evidence Category"

) &&

1678 NStr::Equal

(data_str,

"Antimicrobial Resistance Allele"

) &&

1679 NStr::Equal

(

"Bacterial Antimicrobial Resistance Reference Gene Database"

) ) {

1680 result

"<a href=\"https://www.ncbi.nlm.nih.gov/bioproject/" 1682

"\">"

<< data_str <<

"</a>"

;

1684

}

else if

(

NStr::Equal

(label_str,

"Evidence Accession"

) &&

1685 NStr::Equal

(

"Bacterial Antimicrobial Resistance Reference Gene Database"

) ) {

1686 result

"<a href=\"https://www.ncbi.nlm.nih.gov/nuccore/" 1688

"\">"

<< data_str <<

"</a>"

;

1691 result

"<a href=\"https://www.ncbi.nlm.nih.gov/genome/annotation_prok/evidence/" 1693

"\">"

<< data_str <<

"</a>"

;

1696 result

"<a href=\"https://www.ncbi.nlm.nih.gov/genome/annotation_prok/evidence/" 1698

"\">"

<< data_str <<

"</a>"

;

1712

list<string> &out_lines,

1713 int

&out_prefix_len,

1714 const bool

is_first,

1715 const bool

is_html )

1717 static const int

kFieldLenThreshold = 45;

1720 const char

* prefix =

"##Metadata-START##"

;

1721 const char

* suffix =

"##Metadata-END##"

;

1722 const char

* provider =

""

;

1723 const char

* pipeline =

""

;

1724 const char

* status =

""

;

1725 const char

""

;

1726 const char

* category =

""

;

1727 const char

* organism =

""

;

1729 bool

has_name =

false

;

1731 bool

fieldOverThreshold =

false

;

1735

string::size_type longest_label_len = 1;

1737 if

( (*it_for_len)->GetLabel().IsStr() &&

1738

(*it_for_len)->GetData().IsStr() && ! (*it_for_len)->GetData().GetStr().empty() ) {

1739 const string

= (*it_for_len)->GetLabel().GetStr();

1741 if

(

"StructuredCommentPrefix"

) {

1742

prefix = (*it_for_len)->GetData().GetStr().c_str();

1743

}

else if

(

"StructuredCommentSuffix"

) {

1744

suffix = (*it_for_len)->GetData().GetStr().c_str();

1746 if

(

"Annotation Provider"

) {

1747

provider = (*it_for_len)->GetData().GetStr().c_str();

1748

}

else if

(

"Annotation Pipeline"

) {

1749

pipeline = (*it_for_len)->GetData().GetStr().c_str();

1750

}

else if

(

"Annotation Status"

) {

1751

status = (*it_for_len)->GetData().GetStr().c_str();

1752

}

else if

(

"Annotation Name"

) {

1754

}

else if

(

"URL Organism"

) {

1755

organism = (*it_for_len)->GetData().GetStr().c_str();

1756

}

else if

(

NStr::EqualNocase

(prefix,

"##Evidence-For-Name-Assignment-START##"

)) {

1757 if

(

"Evidence Source"

) {

1758 source

= (*it_for_len)->GetData().GetStr().c_str();

1760 if

(

"Evidence Category"

) {

1761

category = (*it_for_len)->GetData().GetStr().c_str();

1763 if

(

"Evidence Accession"

) {

1764 string

accn = (*it_for_len)->GetData().GetStr();

1769 const

string::size_type label_len =

.length();

1770 if

( (label_len > longest_label_len) && (label_len <= kFieldLenThreshold) ) {

1771

longest_label_len = label_len;

1773 if

( label_len > kFieldLenThreshold ) {

1774

fieldOverThreshold =

true

;

1779

out_prefix_len = (longest_label_len + 4);

1786

out_lines.push_back( prefix );

1787

out_lines.back().append(

"\n"

);

1792 if

( ! (*it)->GetLabel().IsStr() || (*it)->GetLabel().GetStr().empty() ) {

1797 if

( ! (*it)->GetData().IsStr() || (*it)->GetData().GetStr().empty() ) {

1802 if

( (*it)->GetLabel().GetStr() ==

"StructuredCommentPrefix"

1803

(*it)->GetLabel().GetStr() ==

"StructuredCommentSuffix"

1804

(*it)->GetLabel().GetStr() ==

"Annotation Freeze"

1805

(*it)->GetLabel().GetStr() ==

"URL Organism"

) {

1810

out_lines.push_back( (*it)->GetLabel().GetStr() );

1811 string

&next_line = out_lines.back();

1817 if

( ! fieldOverThreshold ) {

1818

next_line.resize(

max

( next_line.size(), longest_label_len),

' '

);

1820

next_line.append(

" :: "

);

1822

provider, pipeline, status, has_name, organism,

, category, accession.c_str() ) );

1823

next_line.append(

"\n"

);

1828

out_lines.push_back( suffix );

1829

out_lines.back().append(

"\n"

);

1837 string

prefix,

, suffix;

1838 switch

( desc.

Which

() ) {

1857 if

( oid.

IsStr

() ) {

1858

prefix =

"Map location: "

;

1862

prefix =

"Map location: (Database "

;

1872

prefix =

"Region: "

;

1893 if

(

.IsStr() &&

.GetStr() ==

"StructuredComment"

) {

1907 if

(

.empty() ||

"."

) {

1929 if

(

.IsStr() &&

.GetStr() ==

"StructuredComment"

) {

1956 if

.Config().IsFormatGBSeq() && !

.Config().IsFormatINSDSeq()) {

1963

(

const string

& prefix,

1964 const string

1965 const string

& suffix,

1970 string

comment = prefix;

1974 if

.Config().IsFormatGBSeq() && !

.Config().IsFormatINSDSeq()) {

1982 size_t

pos = comment.find_last_not_of(

" \n\t\r.~"

);

1983 if

(pos != comment.length() - 1) {

1984 size_t

period = comment.find_last_of(

'.'

);

1985 bool

add_period = period > pos;

2015

<< setw(7) << (prevEndPos)

2017

<< setw(7) << (thisEndPos)

2018

": fragment of "

;

2020 bool

bLengthIsOkay =

true

;

2022

(thisEndPos <= prevEndPos) )

2024

bLengthIsOkay =

false

;

2026

(thisEndPos >= prevEndPos) )

2028

bLengthIsOkay =

false

;

2031 if

( ! bLengthIsOkay ) {

2032 str

"(ERROR: CANNOT CALCULATE LENGTH)"

;

2033

}

else if

( (thisEndPos > uBioseqLength) ||

2034

(prevEndPos > uBioseqLength) )

2036 str

"(ERROR: FRAGMENT IS OUTSIDE BIOSEQ BOUNDS)"

;

2039 str

<< (thisEndPos - prevEndPos + 1);

2041 str

<< (uBioseqLength + thisEndPos - prevEndPos + 1);

2044 str

" bp in length"

;

2055 const string

& build_num) :

2066 if

( uo.

(

"NcbiAnnotation"

) ) {

2074 if

( uo.

(

"NcbiVersion"

) ) {

2078

build_num +=

" version "

;

2084

}

else if

( uo.

(

"Annotation"

) ) {

2088 static const string

prefix =

"NCBI build "

;

2114 const bool

bHtml =

.Config().DoHTML();

2118

ostringstream

;

2120 text

"GENOME ANNOTATION "

<< *refseq <<

": "

;

2122 text

"Features on this sequence have been produced for build " 2128 text

"documentation"

;

2134 text

"NCBI contigs are derived from assembled genomic sequence data." 2136

" Documentation of NCBI's Annotation Process "

;

2141

desc_it; ++desc_it) {

2154 string

s =

.str();

2173

(

const string

& prefix,

2174 const string

& suffix,

2184

hist.

GetDate

().

GetDate

(&date,

"%{%3N%|???%} %{%D%|??%}, %{%4Y%|????%}"

);

2189 if

( (*id)->IsGi() ) {

2190

gis.push_back((*id)->GetGi());

2194

ostringstream

;

2196 text

<< prefix << ((gis.size() > 1) ?

" or before "

" "

) << date

2199 if

( gis.empty() ) {

2221 text

'.'

'\n'

;

2232 if

(

.IsWGSMaster() ||