char OSISReferenceLinks::processText(std::string &text, const SWKey *key, const SWModule *module) {
(void) key;
(void) module;
if (option) return 0;
std::string token;
bool intoken = false;
bool stripThisToken = false;
std::string orig = text;
const char *from = orig.c_str();
for (text = ""; *from; ++from) {
if (*from == '<') {
intoken = true;
token = "";
continue;
}
else if (*from == '>') { // process tokens
intoken = false;
if (std::strncmp(token.c_str(), "reference", 9)
&& std::strncmp(token.c_str(), "/reference", 10)) {
text.push_back('<');
text.append(token);
text.push_back('>');
}
else {
XMLTag tag;
tag = token.c_str();
if (!tag.isEndTag() && type == tag.getAttribute("type") && (!subType.size() || subType == tag.getAttribute("subType"))) {
stripThisToken = true;
continue;
}
else if (tag.isEndTag() && stripThisToken) {
stripThisToken = false;
continue;
}
text.push_back('<');
text.append(token);
text.push_back('>');
}
continue;
}
if (intoken) { //copy token
token.push_back(*from);
}
else { //copy text which is not inside a token
text.push_back(*from);
}
}
return 0;
}
char OSISFootnotes::processText(SWBuf &text, const SWKey *key, const SWModule *module) {
SWBuf token;
bool intoken = false;
bool hide = false;
SWBuf tagText;
XMLTag startTag;
SWBuf refs = "";
int footnoteNum = 1;
char buf[254];
SWKey *p = (module) ? module->createKey() : (key) ? key->clone() : new VerseKey();
VerseKey *parser = SWDYNAMIC_CAST(VerseKey, p);
if (!parser) {
delete p;
parser = new VerseKey();
}
*parser = key->getText();
SWBuf orig = text;
const char *from = orig.c_str();
XMLTag tag;
bool strongsMarkup = false;
for (text = ""; *from; ++from) {
// remove all newlines temporarily to fix kjv2003 module
if ((*from == 10) || (*from == 13)) {
if ((text.length()>1) && (text[text.length()-2] != ' ') && (*(from+1) != ' '))
text.append(' ');
continue;
}
if (*from == '<') {
intoken = true;
token = "";
continue;
}
if (*from == '>') { // process tokens
intoken = false;
if (!strncmp(token, "note", 4) || !strncmp(token.c_str(), "/note", 5)) {
tag = token;
if (!tag.isEndTag()) {
if (tag.getAttribute("type") && (!strcmp("x-strongsMarkup", tag.getAttribute("type"))
|| !strcmp("strongsMarkup", tag.getAttribute("type"))) // deprecated
) {
tag.setEmpty(false); // handle bug in KJV2003 module where some note open tags were <note ... />
strongsMarkup = true;
}
if (!tag.isEmpty()) {
// if ((!tag.isEmpty()) || (SWBuf("strongsMarkup") == tag.getAttribute("type"))) {
refs = "";
startTag = tag;
hide = true;
tagText = "";
continue;
}
}
if (hide && tag.isEndTag()) {
if (module->isProcessEntryAttributes() && !strongsMarkup) { //don`t parse strongsMarkup to EntryAttributes as Footnote
sprintf(buf, "%i", footnoteNum++);
StringList attributes = startTag.getAttributeNames();
for (StringList::const_iterator it = attributes.begin(); it != attributes.end(); it++) {
module->getEntryAttributes()["Footnote"][buf][it->c_str()] = startTag.getAttribute(it->c_str());
}
module->getEntryAttributes()["Footnote"][buf]["body"] = tagText;
startTag.setAttribute("swordFootnote", buf);
if ((startTag.getAttribute("type")) && (!strcmp(startTag.getAttribute("type"), "crossReference"))) {
if (!refs.length())
refs = parser->parseVerseList(tagText.c_str(), *parser, true).getRangeText();
module->getEntryAttributes()["Footnote"][buf]["refList"] = refs.c_str();
}
}
hide = false;
if (option || (startTag.getAttribute("type") && !strcmp(startTag.getAttribute("type"), "crossReference"))) { // we want the tag in the text; crossReferences are handled by another filter
text.append(startTag);
// text.append(tagText); // we don't put the body back in because it is retrievable from EntryAttributes["Footnotes"][]["body"].
}
else continue;
}
strongsMarkup = false;
}
// if not a heading token, keep token in text
//if ((!strcmp(tag.getName(), "reference")) && (!tag.isEndTag())) {
// SWBuf osisRef = tag.getAttribute("osisRef");
if (!strncmp(token, "reference", 9)) {
if (refs.length()) {
refs.append("; ");
}
const char* attr = strstr(token.c_str() + 9, "osisRef=\"");
const char* end = attr ? strchr(attr+9, '"') : 0;
if (attr && end) {
refs.append(attr+9, end-(attr+9));
}
}
if (!hide) {
text.append('<');
text.append(token);
text.append('>');
}
else {
tagText.append('<');
tagText.append(token);
tagText.append('>');
}
continue;
}
if (intoken) { //copy token
token.append(*from);
}
else if (!hide) { //copy text which is not inside a token
text.append(*from);
}
else tagText.append(*from);
}
delete parser;
return 0;
}
char ThMLHeadings::processText(SWBuf &text, const SWKey *key, const SWModule *module) {
SWBuf token;
bool intoken = false;
bool isheader = false;
bool hide = false;
bool preverse = false;
bool withinDiv = false;
SWBuf header;
int headerNum = 0;
int pvHeaderNum = 0;
char buf[254];
XMLTag startTag;
SWBuf orig = text;
const char *from = orig.c_str();
XMLTag tag;
for (text = ""; *from; ++from) {
if (*from == '<') {
intoken = true;
token = "";
continue;
}
if (*from == '>') { // process tokens
intoken = false;
if (!strnicmp(token.c_str(), "div", 3) || !strnicmp(token.c_str(), "/div", 4)) {
withinDiv = (!strnicmp(token.c_str(), "div", 3));
tag = token;
if (hide && tag.isEndTag()) {
if (module->isProcessEntryAttributes() && (option || (!preverse))) {
if (preverse) {
sprintf(buf, "%i", pvHeaderNum++);
module->getEntryAttributes()["Heading"]["Preverse"][buf] = header;
}
else {
sprintf(buf, "%i", headerNum++);
module->getEntryAttributes()["Heading"]["Interverse"][buf] = header;
if (option) { // we want the tag in the text
text.append(header);
}
}
StringList attributes = startTag.getAttributeNames();
for (StringList::const_iterator it = attributes.begin(); it != attributes.end(); it++) {
module->getEntryAttributes()["Heading"][buf][it->c_str()] = startTag.getAttribute(it->c_str());
}
}
hide = false;
if (!option || preverse) { // we don't want the tag in the text anymore
preverse = false;
continue;
}
preverse = false;
}
if (tag.getAttribute("class") && ((!stricmp(tag.getAttribute("class"), "sechead"))
|| (!stricmp(tag.getAttribute("class"), "title")))) {
isheader = true;
if (!tag.isEndTag()) { //start tag
if (!tag.isEmpty()) {
startTag = tag;
/* how do we tell a ThML preverse title from one that should be in the text? probably if any text is before the title... just assuming all are preverse for now
}
if (tag.getAttribute("subtype") && !stricmp(tag.getAttribute("subtype"), "x-preverse")) {
*/
hide = true;
preverse = true;
header = "";
continue;
} // move back up under startTag = tag
}
/* this is where non-preverse will go eventually
if (!tag.isEndTag()) { //start tag
hide = true;
header = "";
if (option) { // we want the tag in the text
text.append('<');
text.append(token);
text.append('>');
}
continue;
}
*/
}
else
isheader = false;
}
if (withinDiv && isheader) {
header.append('<');
header.append(token);
header.append('>');
} else {
// if not a heading token, keep token in text
if (!hide) {
text.append('<');
text.append(token);
text.append('>');
}
}
continue;
}
if (intoken) { //copy token
token.append(*from);
}
else if (!hide) { //copy text which is not inside a token
text.append(*from);
}
else header.append(*from);
}
return 0;
}
char ThMLFootnotes::processText(SWBuf &text, const SWKey *key, const SWModule *module) {
SWBuf token;
bool intoken = false;
bool hide = false;
SWBuf tagText;
XMLTag startTag;
SWBuf refs = "";
int footnoteNum = 1;
char buf[254];
SWKey *p = (module) ? module->createKey() : (key) ? key->clone() : new VerseKey();
VerseKey *parser = SWDYNAMIC_CAST(VerseKey, p);
if (!parser) {
delete p;
parser = new VerseKey();
}
*parser = key->getText();
SWBuf orig = text;
const char *from = orig.c_str();
for (text = ""; *from; from++) {
if (*from == '<') {
intoken = true;
token = "";
continue;
}
if (*from == '>') { // process tokens
intoken = false;
XMLTag tag(token);
if (!strcmp(tag.getName(), "note")) {
if (!tag.isEndTag()) {
if (!tag.isEmpty()) {
refs = "";
startTag = tag;
hide = true;
tagText = "";
continue;
}
}
if (hide && tag.isEndTag()) {
if (module->isProcessEntryAttributes()) {
SWBuf fc = module->getEntryAttributes()["Footnote"]["count"]["value"];
footnoteNum = (fc.length()) ? atoi(fc.c_str()) : 0;
sprintf(buf, "%i", ++footnoteNum);
module->getEntryAttributes()["Footnote"]["count"]["value"] = buf;
StringList attributes = startTag.getAttributeNames();
for (StringList::iterator it = attributes.begin(); it != attributes.end(); it++) {
module->getEntryAttributes()["Footnote"][buf][it->c_str()] = startTag.getAttribute(it->c_str());
}
module->getEntryAttributes()["Footnote"][buf]["body"] = tagText;
startTag.setAttribute("swordFootnote", buf);
if ((startTag.getAttribute("type")) && (!strcmp(startTag.getAttribute("type"), "crossReference"))) {
if (!refs.length())
refs = parser->parseVerseList(tagText.c_str(), *parser, true).getRangeText();
module->getEntryAttributes()["Footnote"][buf]["refList"] = refs.c_str();
}
}
hide = false;
if ((option) || ((startTag.getAttribute("type") && (!strcmp(startTag.getAttribute("type"), "crossReference"))))) { // we want the tag in the text; crossReferences are handled by another filter
text += startTag;
text.append(tagText);
}
else continue;
}
}
// if not a note token, keep token in text
if ((!strcmp(tag.getName(), "scripRef")) && (!tag.isEndTag())) {
SWBuf osisRef = tag.getAttribute("passage");
if (refs.length())
refs += "; ";
refs += osisRef;
}
if (!hide) {
text += '<';
text.append(token);
text += '>';
}
else {
tagText += '<';
tagText.append(token);
tagText += '>';
}
continue;
}
if (intoken) { //copy token
token += *from;
}
else if (!hide) { //copy text which is not inside a token
text += *from;
}
else tagText += *from;
}
delete parser;
return 0;
}
bool OSISHeadings::handleToken(SWBuf &buf, const char *token, BasicFilterUserData *userData) {
MyUserData *u = (MyUserData *)userData;
XMLTag tag(token);
SWBuf name = tag.getName();
// we only care about titles and divs or if we're already in a heading
//
// are we currently in a heading?
if (u->currentHeadingName.size()) {
u->heading.append(u->lastTextNode);
if (name == u->currentHeadingName) {
if (tag.isEndTag(u->sID)) {
if (!u->depth-- || u->sID) {
// see comment below about preverse div changed and needing to preserve the <title> container tag for old school pre-verse titles
// we've just finished a heading. It's all stored up in u->heading
bool canonical = (SWBuf("true") == u->currentHeadingTag.getAttribute("canonical"));
bool preverse = (SWBuf("x-preverse") == u->currentHeadingTag.getAttribute("subType") || SWBuf("x-preverse") == u->currentHeadingTag.getAttribute("subtype"));
// do we want to put anything in EntryAttributes?
if (u->module->isProcessEntryAttributes() && (option || canonical || !preverse)) {
SWBuf buf; buf.appendFormatted("%i", u->headerNum++);
// leave the actual <title...> wrapper in if we're part of an old school preverse title
// because now frontend have to deal with preverse as a div which may or may not include <title> elements
// and they can't simply wrap all preverse material in <h1>, like they probably did previously
SWBuf heading;
if (u->currentHeadingName == "title") {
XMLTag wrapper = u->currentHeadingTag;
if (SWBuf("x-preverse") == wrapper.getAttribute("subType")) wrapper.setAttribute("subType", 0);
else if (SWBuf("x-preverse") == wrapper.getAttribute("subtype")) wrapper.setAttribute("subtype", 0);
heading = wrapper;
heading += u->heading;
heading += tag;
}
else heading = u->heading;
u->module->getEntryAttributes()["Heading"][(preverse)?"Preverse":"Interverse"][buf] = heading;
StringList attributes = u->currentHeadingTag.getAttributeNames();
for (StringList::const_iterator it = attributes.begin(); it != attributes.end(); it++) {
u->module->getEntryAttributes()["Heading"][buf][it->c_str()] = u->currentHeadingTag.getAttribute(it->c_str());
}
}
// do we want the heading in the body?
if (!preverse && (option || canonical)) {
buf.append(u->currentHeadingTag);
buf.append(u->heading);
buf.append(tag);
}
u->suspendTextPassThru = false;
u->clear();
}
}
else u->depth++;
}
u->heading.append(tag);
return true;
}
// are we a title or a preverse div?
else if ( name == "title"
|| (name == "div"
&& ( SWBuf("x-preverse") == tag.getAttribute("subType")
|| SWBuf("x-preverse") == tag.getAttribute("subtype")))) {
u->currentHeadingName = name;
u->currentHeadingTag = tag;
u->heading = "";
u->sID = u->currentHeadingTag.getAttribute("sID");
u->depth = 0;
u->suspendTextPassThru = true;
return true;
}
return false;
}
void x86_mce_callback_register(x86_mce_callback_t cbfunc)
{
mc_callback_bank_extended = cbfunc;
}
/* Machine check recoverable judgement callback handler
* It is used to judge whether an UC error is recoverable by software
*/
static mce_recoverable_t mc_recoverable_scan = NULL;
void mce_recoverable_register(mce_recoverable_t cbfunc)
{
mc_recoverable_scan = cbfunc;
}
/* Judging whether to Clear Machine Check error bank callback handler
* According to Intel latest MCA OS Recovery Writer's Guide,
* whether the error MCA bank needs to be cleared is decided by the mca_source
* and MCi_status bit value.
*/
static mce_need_clearbank_t mc_need_clearbank_scan = NULL;
void mce_need_clearbank_register(mce_need_clearbank_t cbfunc)
{
mc_need_clearbank_scan = cbfunc;
}
/* Utility function to perform MCA bank telemetry readout and to push that
* telemetry towards an interested dom0 for logging and diagnosis.
* The caller - #MC handler or MCA poll function - must arrange that we
* do not migrate cpus. */
/* XXFM Could add overflow counting? */
/* Add out_param clear_bank for Machine Check Handler Caller.
* For Intel latest CPU, whether to clear the error bank status needs to
* be judged by the callback function defined above.
*/
mctelem_cookie_t mcheck_mca_logout(enum mca_source who, cpu_banks_t bankmask,
struct mca_summary *sp, cpu_banks_t* clear_bank)
{
struct vcpu *v = current;
struct domain *d;
uint64_t gstatus, status, addr, misc;
struct mcinfo_global mcg; /* on stack */
struct mcinfo_common *mic;
struct mcinfo_global *mig; /* on stack */
mctelem_cookie_t mctc = NULL;
uint32_t uc = 0, pcc = 0, recover, need_clear = 1 ;
struct mc_info *mci = NULL;
mctelem_class_t which = MC_URGENT; /* XXXgcc */
unsigned int cpu_nr;
int errcnt = 0;
int i;
enum mca_extinfo cbret = MCA_EXTINFO_IGNORED;
cpu_nr = smp_processor_id();
BUG_ON(cpu_nr != v->processor);
mca_rdmsrl(MSR_IA32_MCG_STATUS, gstatus);
memset(&mcg, 0, sizeof (mcg));
mcg.common.type = MC_TYPE_GLOBAL;
mcg.common.size = sizeof (mcg);
if (v != NULL && ((d = v->domain) != NULL)) {
mcg.mc_domid = d->domain_id;
mcg.mc_vcpuid = v->vcpu_id;
} else {
mcg.mc_domid = -1;
mcg.mc_vcpuid = -1;
}
mcg.mc_gstatus = gstatus; /* MCG_STATUS */
switch (who) {
case MCA_MCE_HANDLER:
case MCA_MCE_SCAN:
mcg.mc_flags = MC_FLAG_MCE;
which = MC_URGENT;
break;
case MCA_POLLER:
case MCA_RESET:
mcg.mc_flags = MC_FLAG_POLLED;
which = MC_NONURGENT;
break;
case MCA_CMCI_HANDLER:
mcg.mc_flags = MC_FLAG_CMCI;
which = MC_NONURGENT;
break;
default:
BUG();
}
/* Retrieve detector information */
x86_mc_get_cpu_info(cpu_nr, &mcg.mc_socketid,
&mcg.mc_coreid, &mcg.mc_core_threadid,
&mcg.mc_apicid, NULL, NULL, NULL);
/* If no mc_recovery_scan callback handler registered,
* this error is not recoverable
*/
recover = (mc_recoverable_scan)? 1: 0;
for (i = 0; i < 32 && i < nr_mce_banks; i++) {
struct mcinfo_bank mcb; /* on stack */
/* Skip bank if corresponding bit in bankmask is clear */
if (!test_bit(i, bankmask))
continue;
mca_rdmsrl(MSR_IA32_MC0_STATUS + i * 4, status);
if (!(status & MCi_STATUS_VAL))
continue; /* this bank has no valid telemetry */
/* For Intel Latest CPU CMCI/MCE Handler caller, we need to
* decide whether to clear bank by MCi_STATUS bit value such as
* OVER/UC/EN/PCC/S/AR
*/
if ( mc_need_clearbank_scan )
need_clear = mc_need_clearbank_scan(who, status);
/* If this is the first bank with valid MCA DATA, then
* try to reserve an entry from the urgent/nonurgent queue
* depending on whethere we are called from an exception or
* a poller; this can fail (for example dom0 may not
* yet have consumed past telemetry). */
if (errcnt == 0) {
if ((mctc = mctelem_reserve(which)) != NULL) {
mci = mctelem_dataptr(mctc);
mcinfo_clear(mci);
}
}
memset(&mcb, 0, sizeof (mcb));
mcb.common.type = MC_TYPE_BANK;
mcb.common.size = sizeof (mcb);
mcb.mc_bank = i;
mcb.mc_status = status;
/* form a mask of which banks have logged uncorrected errors */
if ((status & MCi_STATUS_UC) != 0)
uc |= (1 << i);
/* likewise for those with processor context corrupt */
if ((status & MCi_STATUS_PCC) != 0)
pcc |= (1 << i);
if (recover && uc)
/* uc = 1, recover = 1, we need not panic.
*/
recover = mc_recoverable_scan(status);
addr = misc = 0;
if (status & MCi_STATUS_ADDRV) {
mca_rdmsrl(MSR_IA32_MC0_ADDR + 4 * i, addr);
d = maddr_get_owner(addr);
if (d != NULL && (who == MCA_POLLER ||
who == MCA_CMCI_HANDLER))
mcb.mc_domid = d->domain_id;
}
if (status & MCi_STATUS_MISCV)
mca_rdmsrl(MSR_IA32_MC0_MISC + 4 * i, misc);
mcb.mc_addr = addr;
mcb.mc_misc = misc;
if (who == MCA_CMCI_HANDLER) {
mca_rdmsrl(MSR_IA32_MC0_CTL2 + i, mcb.mc_ctrl2);
rdtscll(mcb.mc_tsc);
}
/* Increment the error count; if this is the first bank
* with a valid error then add the global info to the mcinfo. */
if (errcnt++ == 0 && mci != NULL)
x86_mcinfo_add(mci, &mcg);
/* Add the bank data */
if (mci != NULL)
x86_mcinfo_add(mci, &mcb);
if (mc_callback_bank_extended && cbret != MCA_EXTINFO_GLOBAL) {
cbret = mc_callback_bank_extended(mci, i, status);
char OSISMorphSegmentation::processText(SWBuf &text, const SWKey * /*key*/, const SWModule *module) {
SWBuf token;
bool intoken = false;
bool hide = false;
SWBuf orig( text );
const char *from = orig.c_str();
XMLTag tag;
SWBuf tagText = "";
unsigned int morphemeNum = 0;
bool inMorpheme = false;
SWBuf buf;
for (text = ""; *from; ++from) {
if (*from == '<') {
intoken = true;
token = "";
continue;
}
if (*from == '>') { // process tokens
intoken = false;
if (!strncmp(token.c_str(), "seg ", 4) || !strncmp(token.c_str(), "/seg", 4)) {
tag = token;
if (!tag.isEndTag() && tag.getAttribute("type") && !strcmp("morph", tag.getAttribute("type"))) { //<seg type="morph"> start tag
hide = !option; //only hide if option is Off
tagText = "";
inMorpheme = true;
}
if (tag.isEndTag()) {
buf.setFormatted("%.3d", morphemeNum++);
module->getEntryAttributes()["Morpheme"][buf]["body"] = tagText;
inMorpheme = false;
}
if (hide) { //hides start and end tags as long as hide is set
if (tag.isEndTag()) { //</seg>
hide = false;
}
continue; //leave out the current token
}
} //end of seg tag handling
text.append('<');
text.append(token);
text.append('>');
if (inMorpheme) {
tagText.append('<');
tagText.append(token);
tagText.append('>');
}
hide = false;
continue;
} //end of intoken part
if (intoken) { //copy token
token.append(*from);
}
else { //copy text which is not inside of a tag
text.append(*from);
if (inMorpheme) {
tagText.append(*from);
}
}
}
return 0;
}
